Tootfinder

MAI-Image-1: Microsofts erster eigener Bildgenerator
Der Bildgenerator MAI-Image-1 von Microsoft hat seinen ersten Auftritt in der LMArena gemacht.
https://www.heise.de/news/MAI-Image-1-Mi…

AI image generators like Nano Banana have increased realism by mimicking phone camera traits in contrast, exposure, and sharpening to avoid the uncanny valley (Allison Johnson/The Verge)
https://www.theverge.com/column/843883/ai-image-generators-better-worse

AI image generators are getting better by getting worse
AI image generators are getting way better at creating realistic fakes, by making image quality a little bit worse.

🏈 How name, image, and likeness policies boost college football's competitive balance
#sports

How name, image, and likeness policies boost college football's competitive balance
A study published in Management Science challenges conventional wisdom about name, image, and likeness (NIL) policies in college football, demonstrating they actively enhance competitive balance and broaden opportunities for athletes.

Microsoft unveils MAI-Image-1, its first text-to-image AI model developed in house, and says it excels at photorealistic imagery, like lighting and landscapes (Andrew J. Hawkins/The Verge)
https://www.theverge.com/news/798923/microsoft-ai-image-generator-in-house…

Microsoft AI announces first image generator created in-house
Microsoft AI announced a new text-to-image generator developed in-house.

Ordinality of Visible-Thermal Image Intensities for Intrinsic Image Decomposition
Zeqing Leo Yuan, Mani Ramanagopal, Aswin C. Sankaranarayanan, Srinivasa G. Narasimhan
https://arxiv.org/abs/2509.10388 …

Ordinality of Visible-Thermal Image Intensities for Intrinsic Image Decomposition
Decomposing an image into its intrinsic photometric factors--shading and reflectance--is a long-standing challenge due to the lack of extensive ground-truth data for real-world scenes. Recent methods rely on synthetic data or sparse annotations for limited indoor and even fewer outdoor scenes. We introduce a novel training-free approach for intrinsic image decomposition using only a pair of visible and thermal images. We leverage the principle that light not reflected from an opaque surface is …

A silent scenery in four acts...
(Selenium-toned[1] 4x6 salt print (still in final wash) plus previous work-in-progress stages... see alt text for details)
The picture/motif itself is one of my personal favorites and was taken 4 years ago in the Alpstein massif, when clouds were spontaneously forming around us, creating a wonderful light/scene/drama and a dear memory... now also as print which likely will/can outlast myself
[1] The tones will become more neutral once dry...…

TDADL-IE: A Deep Learning-Driven Cryptographic Architecture for Medical Image Security
Junhua Zhou, Quanjun Li, Weixuan Li, Guang Yu, Yihua Shao, Yihang Dong, Mengqian Wang, Zimeng Li, Changwei Gong, Xuhang Chen
https://arxiv.org/abs/2510.11301

TDADL-IE: A Deep Learning-Driven Cryptographic Architecture for Medical Image Security
The rise of digital medical imaging, like MRI and CT, demands strong encryption to protect patient data in telemedicine and cloud storage. Chaotic systems are popular for image encryption due to their sensitivity and unique characteristics, but existing methods often lack sufficient security. This paper presents the Three-dimensional Diffusion Algorithm and Deep Learning Image Encryption system (TDADL-IE), built on three key elements. First, we propose an enhanced chaotic generator using an LST…

Welcome back - been busy the last days with meeting friends etc 🙂
But I wanted to show some more #photos from the #Lotharsteig in the #nationalparkschwarzwald . Different from …

»Britische Regulierer ungehalten — 4chan soll jetzt wirklich Strafe zahlen:
Die britische Regulierungsbehörde Ofcom hat erstmals eine Strafe nach dem neuen Online Safety Act verhängt. Das berüchtigte Image-Forum 4chan soll jetzt wirklich zahlen und sein Verhalten ändern - sonst steigt das Bußgeld täglich weiter an.«
Online-Propaganda wird mal wirklich bestraft und nicht nur darüber gesprochen.
🍀

Britische Regulierer ungehalten: 4chan soll jetzt wirklich Strafe zahlen
Die britische Regulierungsbehörde Ofcom hat erstmals eine Strafe nach dem neuen Online Safety Act verhängt. Das berüchtigte Image-Forum 4chan soll jetzt wirklich zahlen und sein Verhalten ändern - sonst steigt das Bußgeld täglich weiter an.

Efficient Learned Image Compression Through Knowledge Distillation
Fabien Allemand, Attilio Fiandrotti, Sumanta Chaudhuri, Alaa Eddine Mazouz
https://arxiv.org/abs/2509.10366 ht…

Efficient Learned Image Compression Through Knowledge Distillation
Learned image compression sits at the intersection of machine learning and image processing. With advances in deep learning, neural network-based compression methods have emerged. In this process, an encoder maps the image to a low-dimensional latent space, which is then quantized, entropy-coded into a binary bitstream, and transmitted to the receiver. At the receiver end, the bitstream is entropy-decoded, and a decoder reconstructs an approximation of the original image. Recent research sugges…

Embedding the Teacher: Distilling vLLM Preferences for Scalable Image Retrieval
Eric He, Akash Gupta, Adian Liusie, Vatsal Raina, Piotr Molenda, Shirom Chabra, Vyas Raina
https://arxiv.org/abs/2510.12014

Embedding the Teacher: Distilling vLLM Preferences for Scalable Image Retrieval
Text--image retrieval is necessary for applications such as product recommendation. Embedding-based approaches like CLIP enable efficient large-scale retrieval via vector similarity search, but they are primarily trained on literal caption-like text--image pairs and often fail to capture abstract or persona-driven attributes common in product recommendation applications (e.g., ``a gift for a mother who loves gardening''). In contrast, state-of-the-art vision--language models (vLLMs) can align t…

Metropolitana IV 🏯
城 IV 🏯
📷 Pentax MX
🎞️ Ilford Pan 100
#filmphotography #Photography #blackandwhite

Image of a quantum-corrected black hole without Cauchy horizons illuminated by a static thin accretion disk
Shilong Huang, Jiawei Chen, Jinsong Yang
https://arxiv.org/abs/2510.09956

Image of a quantum-corrected black hole without Cauchy horizons illuminated by a static thin accretion disk
Latest advances in effective quantum gravity propose a quantum-corrected black hole solution that avoids Cauchy horizons. In this paper, we study the image of the black hole and explore the influence of the quantum parameter $ζ$ on its image. First, we investigate the influence of $ζ$ on the event horizon, photon sphere, critical impact parameter, and innermost stable circular orbit associated with the black hole. We find that all these quantities exhibit an increase with increasing $ζ$. Mea…

Advancing credibility and transparency in brain-to-image reconstruction research: Reanalysis of Koide-Majima, Nishimoto, and Majima https://arxiv.org/abs/2511.07960 by @… et al.;

Advancing credibility and transparency in brain-to-image reconstruction research: Reanalysis of Koide-Majima, Nishimoto, and Majima (Neural Networks, 2024)
A recent high-profile study by Koide-Majima et al. (2024) claimed a major advance in reconstructing visual imagery from brain activity using a novel variant of a generative AI-based method. However, our independent reanalysis reveals multiple methodological concerns that raise questions about the validity of their conclusions. Specifically, our evaluation demonstrates that: (1) the reconstruction results are biased by selective reporting of only the best-performing examples at multiple levels; …

Weekend #Plankton Factoid 🦠🦐
Most cladocerans have a bivalve carapace, but one genus is very different. Leptodora is globally distributed in the north, large (~2 cm), elongated, and effectively transparent, leading it to be coined "ghost flea" by a colleague. It is a primitive genus and is the only cladoceran with a nauplius stage. Highly predaceous with a huge eye, it preys on juv…

JND-Guided Light-Weight Neural Pre-Filter for Perceptual Image Coding
Chenlong He, Zijing Dong, Min Li, Zhijian Hao, Leilei Huang, Xiaoyang Zeng, Yibo Fan
https://arxiv.org/abs/2510.10648

JND-Guided Light-Weight Neural Pre-Filter for Perceptual Image Coding
Just Noticeable Distortion (JND)-guided pre-filter is a promising technique for improving the perceptual compression efficiency of image coding. However, existing methods are often computationally expensive, and the field lacks standardized benchmarks for fair comparison. To address these challenges, this paper introduces a twofold contribution. First, we develop and open-source FJNDF-Pytorch, a unified benchmark for frequency-domain JND-Guided pre-filters. Second, leveraging this platform, we …

#Blakes7 Series A, Episode 06 - Seek-Locate-Destroy
SERVALAN: Very well, Councillor Bercol. You may tell the President that I am appointing a Space Commander to take absolute control of this matter. He will be exclusively concerned to seek, locate, and destroy Blake.
BERCOL: Oh, excellent, excellent.

The Trump administration is arguing that requiring real-time American Sign Language interpretation of events like White House press briefings
“would severely intrude on the President’s prerogative to control the image he presents to the public,”
part of a lawsuit seeking to require the White House to provide the services.
Department of Justice attorneys haven’t elaborated on how doing so might hamper the portrayal Trump seeks to present to the public.
But overturning p…

White House says sign language services 'intrude' on Trump's public image
The Trump administration argues that providing real-time American Sign Language interpretation for events like White House press briefings would intrude on the president’s control over his public image. This stance is part of a lawsuit filed by the National Association for the Deaf, which claims the lack of ASL interpretation denies deaf Americans access to important communications. The Justice Department suggests alternatives like online transcripts and closed captioning provide what's neede…

White House: ASL Interpreters Hurt Trump's Image - Joe.My.God.
https://www.joemygod.com/2025/12/white-house-asl-interpreters-hurt-trumps-image/

Testing chatbots on the creation of encoders for audio conditioned image generation
Jorge E. Le\'on, Miguel Carrasco
https://arxiv.org/abs/2509.09717 https://

Testing chatbots on the creation of encoders for audio conditioned image generation
On one hand, recent advances in chatbots has led to a rising popularity in using these models for coding tasks. On the other hand, modern generative image models primarily rely on text encoders to translate semantic concepts into visual representations, even when there is clear evidence that audio can be employed as input as well. Given the previous, in this work, we explore whether state-of-the-art conversational agents can design effective audio encoders to replace the CLIP text encoder from …

September 2025 war weltweit der drittwärmste seit Beginn der Aufzeichnungen.
Laut dem #Copernicus Climate Change Service lag die globale Durchschnittstemperatur bei 16,11 °C – 0,66 °C über dem Mittelwert von 1991–2020.
In #Europa betrug die Abweichung sogar 1,23 °C. Solche

I wonder what graven image moses would have to say about me using the graven image chat app ("Text With Jesus")

Hybrid Vision Transformer and Quantum Convolutional Neural Network for Image Classification
Mingzhu Wang, Yun Shang
https://arxiv.org/abs/2510.12291 https://

Hybrid Vision Transformer and Quantum Convolutional Neural Network for Image Classification
Quantum machine learning (QML) holds promise for computational advantage, yet progress on real-world tasks is hindered by classical preprocessing and noisy devices. We introduce ViT-QCNN-FT, a hybrid framework that integrates a fine-tuned Vision Transformer with a quantum convolutional neural network (QCNN) to compress high-dimensional images into features suited for noisy intermediate-scale quantum (NISQ) devices. By systematically probing entanglement, we show that ansatzes with uniformly dis…

Image reconstruction with the JWST Interferometer
Max Charles, Louis Desdoigts, Benjamin Pope, Peter Tuthill, Dori Blakely, Doug Johnstone, Shrishmoy Ray, K. E. Saavik Ford, Barry McKernan, Anand Sivaramakrishnan
https://arxiv.org/abs/2510.10924

Image reconstruction with the JWST Interferometer
Flying on board the James Webb Space Telescope (JWST) above Earth's turbulent atmosphere, the Aperture Masking Interferometer (AMI) on the NIRISS instrument is the highest-resolution infrared interferometer ever placed in space. However, its performance was found to be limited by non-linear detector systematics, particularly charge migration - or the Brighter-Fatter Effect. Conventional interferometric Fourier observables are degraded by non-linear transformations in the image plane, with the c…

RE: https://mastodon.social/@fes4ever/115350527094368974
Describe your Mastodon account in a single image

Image detection-based high-throughput sorting of particles using traveling surface acoustic waves in microscale flows
Nikhil Sethia, Joseph Sushil Rao, Amit Manicka, Michael L. Etheridge, Erik B. Finger, John C. Bischof, Cari S. Dutcher
https://arxiv.org/abs/2509.09692

Image detection-based high-throughput sorting of particles using traveling surface acoustic waves in microscale flows
Large particle sorters have potential applications in sorting microplastics and large biomaterials (>50 micrometer), such as tissues, spheroids, organoids, and embryos. Though great advancements have been made in image-based sorting of cells and particles (<50 micrometer), their translation for high-throughput sorting of larger biomaterials and particles (>50 micrometer) has been more limited. An image-based detection technique is highly desirable due to richness of the data (including size, sh…

Kicking off the @… annual meeting with some insitu observations with #ECR Shenjie Zhou.
Get the data preprint at the QR code in the image below. Will also go into @soos map

Image reconstruction with the #JWST Interferometer / AMIGO - a Data-Driven Calibration of the JWST Interferometer: https://arxiv.org/abs/2510.10924 / https://arxiv.org/abs/2510.09806 -> How we sharpened the James Webb telescope’s vision from a million kilometres away: https://theconversation.com/how-we-sharpened-the-james-webb-telescopes-vision-from-a-million-kilometres-away-262510 -> thread https://bsky.app/profile/benjaminpope.bsky.social/post/3m34san6dd22m

Immunizing Images from Text to Image Editing via Adversarial Cross-Attention
Matteo Trippodo, Federico Becattini, Lorenzo Seidenari
https://arxiv.org/abs/2509.10359 https://

Immunizing Images from Text to Image Editing via Adversarial Cross-Attention
Recent advances in text-based image editing have enabled fine-grained manipulation of visual content guided by natural language. However, such methods are susceptible to adversarial attacks. In this work, we propose a novel attack that targets the visual component of editing methods. We introduce Attention Attack, which disrupts the cross-attention between a textual prompt and the visual representation of the image by using an automatically generated caption of the source image as a proxy for t…

Anybody know of a Linux image editing tool that lets you dynamically mesh-warp a layer (i.e. click a point in the image and move it to align with a feature on another layer, adding new mesh key points each time you do this)?

#IsraelIsATerroristState

Reblog by @sadabeuk · 1 image
💬 0  🔁 19838  ❤️ 16208 · This should be a bigger news tbh

From pinterest apparently.

Kein Helm und keine Warnweste kann unsere Kinder vor den Verbrechen des rechtsextremen Terrors schützen.
Joseph Karel Vos wurde 11 Jahre, dann ermordeten ihn die Nazis in einer Gaskammer zusammen 666 anderen Menschen.
Die Bundesregierung, geführt von der CDU, ist auf bestem Wege den ideolgischen Nachfahren der Nazis wieder zur Macht zu verhelfen - statt sie zu bekämpfen, übernehmen sie ihre Positionen und führen politischen Machtkampf gegen andere demokratische Parteien

Auschwitz Memorial (@auschwitzmuseum@mastodon.world)
Attached: 1 image 15 September 1931. | A Dutch Jewish boy, Joseph Karel Vos, was born in Kempen. He arrived at #Auschwitz on 26 November 1942 in a transport of 709 Jews deported from #Westerbork. He was among 667 of them murdered in gas chambers after the selection.

Been playing with what kind of image to use in the fake window. Some beachy sunset as though looking out from a beach bar?
Maybe that's too lazy just based on the window blind I made a couple of years back. Will I sleep paranoid I'm being watched by Krux?

Die @… ist auf Mastodon. Also sie war hier. Denn sie ist auf der Flucht in die BigTech Netzwerke.
Dass sie hier kaum Resonanz bekommen haben, liegt möglicherweise an der Form der Postings: hauptsächlich waren es glatte PR Sprüche mit Sharepics. Kaum echte Interaktion. Ich wundere mich nicht, warum sie es niemals in meine Timline geschafft haben.
Ich w…

UNO-Flüchtlingshilfe (@unoflucht@bonn.social)
Attached: 1 image Wir verabschieden uns von diesem Kanal – aber nicht von Euch! Unser Account bleibt bestehen, damit Informationen weiterhin zugänglich sind. Neue Posts gibt es künftig auf unseren anderen Plattformen. Bleibt mit uns verbunden 👇

How is it that #PalestineAction, whose worst 'crime' is to spray paint aeroplanes, is declared a #Terrorist organisation, and the #IDF, whose soldiers routinely beat and rape prisoners, shoot ch…

When I am King, all graphs will be required to use the label "lots" along the Y-axis.
https://mastodon.gamedev.place/@eniko/115373539503634831

Eniko Fox (@eniko@mastodon.gamedev.place)
Attached: 1 image people will be like "i've got the summer flu" and this is the wastewater graph for their area

Achievement of the day:
Produce the same output as me_cleaner for a ThinkPad X270 image.
A few hardcoded assumptions and no extra options at this point.
Off to a good start! 🥳✨👩‍💻

WPP and Google strike a $400M deal to embed Google's AI tools like Veo in WPP marketing and give WPP early access to Google's latest video and image models (Daniel Thomas/Financial Times)
https://www.ft.com/content/ccf5ea33-1398-4b9d-8bf6-a403f2f5493e
…

Time For 9 o'clock #HashTagGames hosted by @…
#ScandalousFoods

Elevating Medical Image Security: A Cryptographic Framework Integrating Hyperchaotic Map and GRU
Weixuan Li, Guang Yu, Quanjun Li, Junhua Zhou, Jiajun Chen, Yihang Dong, Mengqian Wang, Zimeng Li, Changwei Gong, Lin Tang, Xuhang Chen
https://arxiv.org/abs/2510.12084

Elevating Medical Image Security: A Cryptographic Framework Integrating Hyperchaotic Map and GRU
Chaotic systems play a key role in modern image encryption due to their sensitivity to initial conditions, ergodicity, and complex dynamics. However, many existing chaos-based encryption methods suffer from vulnerabilities, such as inadequate permutation and diffusion, and suboptimal pseudorandom properties. This paper presents Kun-IE, a novel encryption framework designed to address these issues. The framework features two key contributions: the development of the 2D Sin-Cos Pi Hyperchaotic Ma…

NOTHING is forever...
Here are tips for how to stop the latest MacOS upgrade now, and if you want, until the end of support comes years later.
Apple is good at supporting old stuff, but they're bound to get worse at it. Everything's changing faster and faster, and nefarious bad guys make security harder and harder.
#Security

Cult of Mac (@cultofmac@mastodon.social)
Attached: 1 image Secret trick will stop your iPhone from updating to iOS 26 — forever! https://www.cultofmac.com/how-to/stop-ios-update?utm_source=dlvr.it&utm_medium=mastodon

big head moment while walking home from the pub in the rain

Just suspended/defederated the zhub.link domain that appears to be a white supremacist/hate speech instance whose admin is going around harassing Palestinians and allies on the fediverse and is/was apparently also hosting an account disseminating CSAM (https://hear-me.social/@admin/11266673170955…

On The Road - To Xi’An/ Angles ↕️
在路上 - 去西安/ 角度 ↕️
📷 Pentax MX
🎞️Fujifilm Neopan F, expired 1993
#filmphotography #Photography #blackandwhite

Series A, Episode 12 - Deliverance
SERVALAN: Yes?
VOICE: [V.O.] Space Commander Travis is here.
SERVALAN: Send him in. [Travis enters and stands before Servalan's desk. She ignores him for a moment, concentrating on something else.]
https://blake.torpidity.net/m/112/224 B7B4<…

A Lightweight Ensemble-Based Face Image Quality Assessment Method with Correlation-Aware Loss
MohammadAli Hamidi, Hadi Amirpour, Luigi Atzori, Christian Timmerer
https://arxiv.org/abs/2509.10114

A Lightweight Ensemble-Based Face Image Quality Assessment Method with Correlation-Aware Loss
Face image quality assessment (FIQA) plays a critical role in face recognition and verification systems, especially in uncontrolled, real-world environments. Although several methods have been proposed, general-purpose no-reference image quality assessment techniques often fail to capture face-specific degradations. Meanwhile, state-of-the-art FIQA models tend to be computationally intensive, limiting their practical applicability. We propose a lightweight and efficient method for FIQA, designe…

Google rolls out Nano Banana image editing upgrades in Photos, including a "help me edit" feature that lets users make edits using text or voice prompts (Elyse Betters Picaro/ZDNET)
https://www.zdnet.com/article/your-google-

Your Google Photos just got 3 huge Nano Banana image editing upgrades - for free
Google Photos just made it easier than ever to create realistic AI edits, thanks to Google DeepMind's top image-editing model.

Continuing a bit with the #photos from our #schwarzwald #vacations : (unknowingly) we walked along the Western-way. It was pretty cool because the trail was very diverse as you can see on the photo…

SynthID-Image: Image watermarking at internet scale
Sven Gowal, Rudy Bunel, Florian Stimberg, David Stutz, Guillermo Ortiz-Jimenez, Christina Kouridi, Mel Vecerik, Jamie Hayes, Sylvestre-Alvise Rebuffi, Paul Bernard, Chris Gamble, Mikl\'os Z. Horv\'ath, Fabian Kaczmarczyck, Alex Kaskasoli, Aleksandar Petrov, Ilia Shumailov, Meghana Thotakuri, Olivia Wiles, Jessica Yung, Zahra Ahmed, Victor Martin, Simon Rosen, Christopher Sav\v{c}ak, Armin Senoner, Nidhi Vyas, Pushmeet Kohli

SynthID-Image: Image watermarking at internet scale
We introduce SynthID-Image, a deep learning-based system for invisibly watermarking AI-generated imagery. This paper documents the technical desiderata, threat models, and practical challenges of deploying such a system at internet scale, addressing key requirements of effectiveness, fidelity, robustness, and security. SynthID-Image has been used to watermark over ten billion images and video frames across Google's services and its corresponding verification service is available to trusted test…

Replaced article(s) found for eess.IV. https://arxiv.org/list/eess.IV/new
[1/1]:
- Rethinking Medical Anomaly Detection in Brain MRI: An Image Quality Assessment Perspective
Pan, Xia, Yan, Xu, Qin, Li, Wu, Jia, Chen, Shi

Moody Urbanity - Relations VI 🧬
情绪化城市 - 关系 VI 🧬
📷 Zeiss IKON Super Ikonta 533/16
🎞️ Ilford HP5 400, expired 1993
#filmphotography #Photography #blackandwhite

The HRRR, a NOAA real-time 3-km resolution, hourly updated, cloud-resolving, convection-allowing atmospheric model, initialized by 3km grids with 3km radar assimilation,
predicts a whole lotta water will fall on coastal Southern California in the early morning https://m.ai6yr.org/@ai6yr/11555228330

AI6YR Ben (@ai6yr@m.ai6yr.org)
Attached: 1 image HRRR says... 5am. TBD if the forecast pans out, but HRRR usually is good. #rain #CAwx

InfGen: A Resolution-Agnostic Paradigm for Scalable Image Synthesis
Tao Han, Wanghan Xu, Junchao Gong, Xiaoyu Yue, Song Guo, Luping Zhou, Lei Bai
https://arxiv.org/abs/2509.10441

InfGen: A Resolution-Agnostic Paradigm for Scalable Image Synthesis
Arbitrary resolution image generation provides a consistent visual experience across devices, having extensive applications for producers and consumers. Current diffusion models increase computational demand quadratically with resolution, causing 4K image generation delays over 100 seconds. To solve this, we explore the second generation upon the latent diffusion models, where the fixed latent generated by diffusion models is regarded as the content representation and we propose to decode arbit…

Series B, Episode 08 - Hostage
MUTOID: Yes, Supreme Commander. Time distort ten.
SERVALAN: Mutoids. Don't you ever question anything?
https://blake.torpidity.net/m/208/384 B7B4

Finally an RGB image of comet #3IATLAS from images taken by #GeminiNorth during the 26 November #shadowTheScientists session: https://noirlab.edu/public/news/noirlab2532/ - the coma has become bluer due to more gas emission. Also published today: an X-ray image by XMM-Newton at https://www.esa.int/ESA_Multimedia/Images/2025/12/XMM-Newton_sees_comet_3I_ATLAS_in_X-ray_light with explanations in http://www.cbat.eps.harvard.edu/iau/cbet/005600/CBET005646.txt which also contains more 3I news.
Meanwhile the paper https://iopscience.iop.org/article/10.3847/2515-5172/ae2915 claims an upper limit for 3I's nucleus diameter of only some 750 meters from the measured non-gravitational acceleration (NGA) parameters: that would be waaay more stringent than the 5.6 km upper limit from early Hubble observations reported in https://iopscience.iop.org/article/10.3847/2041-8213/adf8d8 (where also a lower limit of 440 meters is stated).

Da hat wohl jemand das #Gehupe satt:
https://mastodon.social/@BundestagPetitionenNewsbot/115208317518312911

Bundestag Petitionen Newsbot (@BundestagPetitionenNewsbot@mastodon.social)
Attached: 1 image Es wurde eine neue #Petition gestartet: Titel: #Untersagung der #Signalgebung durch die #Bahn vor unbeschrankten #Bahnübergängen Mitzeichnungen: 0 Es fehlen noch 30000 Stimmen. Die Mitzeichnungsfrist endet in 42 Tagen am 27.10.2025. Link: https://epetitionen.bundestag.de/petitionen/_2025/_09/_02/Petition_186008.nc.html #neueBTP #Bundestag #Petitionsausschuss

Time For 9 o'clock #HashTagGames hosted by @… Let's play!
#HairStyleABookOrPlay

MonochromeEvolutionaryBioDigitalMultiCellularSymbiosisStruggle
(Selected stills from my infinitely evolving C-SCAPE project, 2022 - made with #MonochromeMonday

Replaced article(s) found for eess.IV. https://arxiv.org/list/eess.IV/new
[1/1]:
- PL-Net: Progressive Learning Network for Medical Image Segmentation
Kunpeng Mao, Ruoyu Li, Junlong Cheng, Danmei Huang, Zhiping Song, ZeKui Liu

Series B, Episode 12 - The Keeper
FOOL: [Singing] I sing you of the Tents, my Master, Charl of the Goths, I sing you of the golden tents, Where your fathers wait to greet you...
BLAKE: [Examining the talisman] It's gone, the brain print's gone!
https://blake.torpidity.net/m/212/515…

DiT360: High-Fidelity Panoramic Image Generation via Hybrid Training
Haoran Feng, Dizhe Zhang, Xiangtai Li, Bo Du, Lu Qi
https://arxiv.org/abs/2510.11712 https://

DiT360: High-Fidelity Panoramic Image Generation via Hybrid Training
In this work, we propose DiT360, a DiT-based framework that performs hybrid training on perspective and panoramic data for panoramic image generation. For the issues of maintaining geometric fidelity and photorealism in generation quality, we attribute the main reason to the lack of large-scale, high-quality, real-world panoramic data, where such a data-centric view differs from prior methods that focus on model design. Basically, DiT360 has several key modules for inter-domain transformation a…

#FotoVorschlag 'Adventliches' / Advent
My wife was gifted two #Lego sets. And this was one of it. It fits super cool to the season and into our appartement.
Happy third #advent if…

Google adds Gemini 2.5 Flash Image, aka Nano Banana, to Search's AI Mode and Google Lens, on Android in the US for those with an account opted into Search Lab (Abner Li/9to5Google)
https://9to5google.com/2025/10/11/google-lens-ai-mode-nano-banana/

Nano Banana image editing comes to AI Mode and Google Lens
Nano Banana has been a hit in the Gemini app, and Google is now bringing image editing and generation to AI Mode, as well as Google Lens.

Time For 9 o'clock #HashTagGames hosted by @… Let's play!
#IrritateASitcomCharacter

Series D, Episode 03 - Traitor
SOOLIN: Teleport operating. [Teleport sound. Dayna and Tarrant arrive]
VILA: What are you smirking about? Do you realize we've got half the Federation battle fleet looking for us?
https://blake.torpidity.net/m/403/495 B7B3

Moody Urbanity - UP 🔝
情绪化城市 - 上面 🔝
📷 Nikon FE
🎞️ Ilford HP5 Plus 400, expired 1993
#filmphotography #Photography #blackandwhite

Realism Control One-step Diffusion for Real-World Image Super-Resolution
Zongliang Wu, Siming Zheng, Peng-Tao Jiang, Xin Yuan
https://arxiv.org/abs/2509.10122 https://

Realism Control One-step Diffusion for Real-World Image Super-Resolution
Pre-trained diffusion models have shown great potential in real-world image super-resolution (Real-ISR) tasks by enabling high-resolution reconstructions. While one-step diffusion (OSD) methods significantly improve efficiency compared to traditional multi-step approaches, they still have limitations in balancing fidelity and realism across diverse scenarios. Since the OSDs for SR are usually trained or distilled by a single timestep, they lack flexible control mechanisms to adaptively prioriti…

Good morning! For this #silentSunday I want to share this #foggy path with you.
I was on my way down and when I entered the fog, temperature really dropped. Actually I didn't want to stop or slow down in order to avoid cooling out.
But at this spot I had to take a quick break for…

Beyond Seeing: Evaluating Multimodal LLMs on Tool-Enabled Image Perception, Transformation, and Reasoning
Xingang Guo, Utkarsh Tyagi, Advait Gosai, Paula Vergara, Ernesto Gabriel Hern\'andez Montoya, Chen Bo Calvin Zhang, Bin Hu, Yunzhong He, Bing Liu, Rakshith Sharma Srinivasa
https://arxiv.org/abs/2510.12712

Beyond Seeing: Evaluating Multimodal LLMs on Tool-Enabled Image Perception, Transformation, and Reasoning
Multimodal Large Language Models (MLLMs) are increasingly applied in real-world scenarios where user-provided images are often imperfect, requiring active image manipulations such as cropping, editing, or enhancement to uncover salient visual cues. Beyond static visual perception, MLLMs must also think with images: dynamically transforming visual content and integrating it with other tools to solve complex tasks. However, this shift from treating vision as passive context to a manipulable cogni…

Series C, Episode 02 - Powerplay
RECEPTIONIST: We have to move on to health reception. You can go together if you wish.
VILA: Oh, thank you.
CALLY: We'd like that, thank you.
RECEPTIONIST: This way.
VILA: Thank you.
https://blake.torpidity.net/m/302/416 B7B5

Google updates NotebookLM's Video Overviews, adding six new Nano Banana-powered visual styles and a new "Brief" format for quick insights (Abner Li/9to5Google)
https://9to5google.com/2025/10/13/notebooklm-video-overviews-styles/

NotebookLM Video Overviews add Nano Banana visual styles, Brief or Explainer formats
NotebookLM is giving Video Overviews a big upgrade with the help of Google’s Nano Banana image editing and generation model.

PhySIC: Physically Plausible 3D Human-Scene Interaction and Contact from a Single Image
Pradyumna Yalandur Muralidhar, Yuxuan Xue, Xianghui Xie, Margaret Kostyrko, Gerard Pons-Moll
https://arxiv.org/abs/2510.11649

PhySIC: Physically Plausible 3D Human-Scene Interaction and Contact from a Single Image
Reconstructing metrically accurate humans and their surrounding scenes from a single image is crucial for virtual reality, robotics, and comprehensive 3D scene understanding. However, existing methods struggle with depth ambiguity, occlusions, and physically inconsistent contacts. To address these challenges, we introduce PhySIC, a framework for physically plausible Human-Scene Interaction and Contact reconstruction. PhySIC recovers metrically consistent SMPL-X human meshes, dense scene surface…

Series D, Episode 11 - Orbit
SERVALAN: Don't concern yourself, Egrorian. I encourage ambition.
EGRORIAN: I never conspired against you, I swear it! Orac, acknowledge my instructions. [Orac buzzes, but says nothing.] I don't understand.
https://blake.torpidity.net/m/411/363 B7B3…

When I was walking down from the mountains recently I noticed the frost on the trees and branches -- and some single leafs that were still around.
I really liked this extra touch of color in the grey surrounding. And that it's just a little detail on the huge mountain.
#photography #winter

MagicMirror: A Large-Scale Dataset and Benchmark for Fine-Grained Artifacts Assessment in Text-to-Image Generation
Jia Wang, Jie Hu, Xiaoqi Ma, Hanghang Ma, Yanbing Zeng, Xiaoming Wei
https://arxiv.org/abs/2509.10260

MagicMirror: A Large-Scale Dataset and Benchmark for Fine-Grained Artifacts Assessment in Text-to-Image Generation
Text-to-image (T2I) generation has achieved remarkable progress in instruction following and aesthetics. However, a persistent challenge is the prevalence of physical artifacts, such as anatomical and structural flaws, which severely degrade perceptual quality and limit application. Given the diversity and complexity of these artifacts, a systematic and fine-grained evaluation framework is required, which is lacking in current benchmarks. To fill this gap, we introduce MagicMirror, a comprehens…

Series A, Episode 13 - Orac
CALLY: We should keep on moving, they could be right behind us.
BLAKE: Yes, without weapons we don't stand a chance. Look, you keep going. I'm going to stay here and try and bring the roof down - block them off.
https://blake.torpidity.net/m/113/347 …

UniFusion: Vision-Language Model as Unified Encoder in Image Generation
Kevin Li, Manuel Brack, Sudeep Katakol, Hareesh Ravi, Ajinkya Kale
https://arxiv.org/abs/2510.12789 https…

UniFusion: Vision-Language Model as Unified Encoder in Image Generation
Although recent advances in visual generation have been remarkable, most existing architectures still depend on distinct encoders for images and text. This separation constrains diffusion models' ability to perform cross-modal reasoning and knowledge transfer. Prior attempts to bridge this gap often use the last layer information from VLM, employ multiple visual encoders, or train large unified models jointly for text and image generation, which demands substantial computational resources and l…

Series C, Episode 05 - The Harvest of Kairos
INTERCEPTOR LEADER: [V.O.] Interceptor Leader to Control. Request instructions!
SERVALAN: Hold position, Interceptor Leader, and wait for instructions from Assault Leader One. We will attack when the Liberator breaks out of Alpha Sector. Four should do it nicely. Well, Dastor, I think it's time we had a little strategic counsel. Bring this - Jarvik to me.

I have some more #photos from the lake from the previous post 😄
For these I went on another side of the lake where there were quite some heather around. - While my wife was taking a small snack, I walked around and searched for nice foregrounds with which I could play and make an appealing memory
And even though I'd also have taken a small rest, I'm more than happy that I spe…

GAMMA: Generalizable Alignment via Multi-task and Manipulation-Augmented Training for AI-Generated Image Detection
Haozhen Yan, Yan Hong, Suning Lang, Jiahui Zhan, Yikun Ji, Yujie Gao, Jun Lan, Huijia Zhu, Weiqiang Wang, Jianfu Zhang
https://arxiv.org/abs/2509.10250

GAMMA: Generalizable Alignment via Multi-task and Manipulation-Augmented Training for AI-Generated Image Detection
With generative models becoming increasingly sophisticated and diverse, detecting AI-generated images has become increasingly challenging. While existing AI-genereted Image detectors achieve promising performance on in-distribution generated images, their generalization to unseen generative models remains limited. This limitation is largely attributed to their reliance on generation-specific artifacts, such as stylistic priors and compression patterns. To address these limitations, we propose G…

Series D, Episode 02 - Power
TARRANT: [Disbelieving] Telekinesis?
ORAC: The power to move objects at a distance using only the mind-
DAYNA: [Cutting him off] Yes, we know what it means.
https://blake.torpidity.net/m/402/445 B7B2

Series C, Episode 05 - The Harvest of Kairos
SHAD: [On screen] Yes, madam.
[Launch platform]
GUARD: Instructions from the Captain. You are to wait for the next shuttle.
CARLON: But there isn't another.
GUARD: One will be sent for you tomorrow.
https://blake.torpidity.net/m/305/214

Series B, Episode 04 - Horizon
KOMMISSAR: [O.O.V.] Your companions are still alive.
CALLY: I feel it. You killed him. You killed him because he would not obey you.
KOMMISSAR: What is she talking about?
https://blake.torpidity.net/m/204/416 B7B3

#Blakes7 Series B, Episode 05 - Pressure Point
SERVALAN: If you tell me about the rendezvous, I will consider sparing your life.
KASABI: My life isn't yours to spare.
SERVALAN: Oh, but it is.
https://blake.torpidity.ne…

Efficient Perceptual Image Super Resolution: AIM 2025 Study and Benchmark
Bruno Longarela, Marcos V. Conde, Alvaro Garcia, Radu Timofte
https://arxiv.org/abs/2510.12765 https://…

Efficient Perceptual Image Super Resolution: AIM 2025 Study and Benchmark
This paper presents a comprehensive study and benchmark on Efficient Perceptual Super-Resolution (EPSR). While significant progress has been made in efficient PSNR-oriented super resolution, approaches focusing on perceptual quality metrics remain relatively inefficient. Motivated by this gap, we aim to replicate or improve the perceptual results of Real-ESRGAN while meeting strict efficiency constraints: a maximum of 5M parameters and 2000 GFLOPs, calculated for an input size of 960x540 pixels…

Series D, Episode 10 - Gold
SOOLIN: [Searching Keiller.] He's clean.
KEILLER: Of course I'm clean, what do you take me for. Avon and I are old friends. It's good to see you, Avon.
DAYNA: Uh, nobody said move, Keiller. Just relax.
https://blake.torpidity.net/m/410/6 B7B3…

Zero-Shot CFC: Fast Real-World Image Denoising based on Cross-Frequency Consistency
Yanlin Jiang, Yuchen Liu, Mingren Liu
https://arxiv.org/abs/2510.12646 https://

Zero-Shot CFC: Fast Real-World Image Denoising based on Cross-Frequency Consistency
Zero-shot denoisers address the dataset dependency of deep-learning-based denoisers, enabling the denoising of unseen single images. Nonetheless, existing zero-shot methods suffer from long training times and rely on the assumption of noise independence and a zero-mean property, limiting their effectiveness in real-world denoising scenarios where noise characteristics are more complicated. This paper proposes an efficient and effective method for real-world denoising, the Zero-Shot denoiser bas…

Series D, Episode 13 - Blake
BLAKE: Oh, most of it wasn't on Earth, Tarrant. Not what happened to me. [Arlen enters, Blake turns, Tarrant kicks the gun out of Blake's hand, shoves him into Arlen, and bolts out of the room, strongarming Deva on the way.]
ARLEN: Do you want him killed?!
https://blake.torpidity.net/m/413/…

Series B, Episode 01 - Redemption
BLAKE: Zen, identify the hostiles.
CALLY: Forty-two seconds.
BLAKE: Zen! [Zen burbles]
AVON: The information must be bypassing the translator systems.
CALLY: Thirty-five seconds.
https://blake.torpidity.net/m/201/97 B7B3

Benchmarking foundation models for hyperspectral image classification: Application to cereal crop type mapping
Walid Elbarz, Mohamed Bourriz, Hicham Hajji, Hamd Ait Abdelali, Fran\c{c}ois Bourzeix
https://arxiv.org/abs/2510.11576

Benchmarking foundation models for hyperspectral image classification: Application to cereal crop type mapping
Foundation models are transforming Earth observation, but their potential for hyperspectral crop mapping remains underexplored. This study benchmarks three foundation models for cereal crop mapping using hyperspectral imagery: HyperSigma, DOFA, and Vision Transformers pre-trained on the SpectralEarth dataset (a large multitemporal hyperspectral archive). Models were fine-tuned on manually labeled data from a training region and evaluated on an independent test region. Performance was measured w…

Series D, Episode 02 - Power
VILA: Not too close. The gap is all connected with the thickness of the door. So what's the difference between Seskas and Hommiks?
PELLA: How do you know how thick it is?
VILA: By the stress pattern.
https://blake.torpidity.net/m/402/132 B7B4

Zero-shot image privacy classification with Vision-Language Models
Alina Elena Baia, Alessio Xompero, Andrea Cavallaro
https://arxiv.org/abs/2510.09253 https://

Zero-shot image privacy classification with Vision-Language Models
While specialized learning-based models have historically dominated image privacy prediction, the current literature increasingly favours adopting large Vision-Language Models (VLMs) designed for generic tasks. This trend risks overlooking the performance ceiling set by purpose-built models due to a lack of systematic evaluation. To address this problem, we establish a zero-shot benchmark for image privacy classification, enabling a fair comparison. We evaluate the top-3 open-source VLMs, accor…

Series B, Episode 02 - Shadow
BLAKE: There's no reason why they should.
[Space City. Chairman is seen on communications screen]
ENFORCER: They'll be making planetfall anytime now.
CHAIRMAN: Excellent. Are all Largo's addicts so available?
https://blake.torpidity.net/m/202/444

TerraCodec: Compressing Earth Observations
Julen Costa-Watanabe, Isabelle Wittmann, Benedikt Blumenstiel, Konrad Schindler
https://arxiv.org/abs/2510.12670 https://

TerraCodec: Compressing Earth Observations
Earth observation (EO) satellites produce massive streams of multispectral image time series, posing pressing challenges for storage and transmission. Yet, learned EO compression remains fragmented, lacking publicly available pretrained models and misaligned with advances in compression for natural imagery. Image codecs overlook temporal redundancy, while video codecs rely on motion priors that fail to capture the radiometric evolution of largely static scenes. We introduce TerraCodec (TEC), a …

PET Head Motion Estimation Using Supervised Deep Learning with Attention
Zhuotong Cai, Tianyi Zeng, Jiazhen Zhang, El\'eonore V. Lieffrig, Kathryn Fontaine, Chenyu You, Enette Mae Revilla, James S. Duncan, Jingmin Xin, Yihuan Lu, John A. Onofrey
https://arxiv.org/abs/2510.12758

PET Head Motion Estimation Using Supervised Deep Learning with Attention
Head movement poses a significant challenge in brain positron emission tomography (PET) imaging, resulting in image artifacts and tracer uptake quantification inaccuracies. Effective head motion estimation and correction are crucial for precise quantitative image analysis and accurate diagnosis of neurological disorders. Hardware-based motion tracking (HMT) has limited applicability in real-world clinical practice. To overcome this limitation, we propose a deep-learning head motion correction a…

Detecting Text Manipulation in Images using Vision Language Models
Vidit Vidit, Pavel Korshunov, Amir Mohammadi, Christophe Ecabert, Ketan Kotwal, S\'ebastien Marcel
https://arxiv.org/abs/2509.10278

Detecting Text Manipulation in Images using Vision Language Models
Recent works have shown the effectiveness of Large Vision Language Models (VLMs or LVLMs) in image manipulation detection. However, text manipulation detection is largely missing in these studies. We bridge this knowledge gap by analyzing closed- and open-source VLMs on different text manipulation datasets. Our results suggest that open-source models are getting closer, but still behind closed-source ones like GPT- 4o. Additionally, we benchmark image manipulation detection-specific VLMs for te…

ViCO: A Training Strategy towards Semantic Aware Dynamic High-Resolution
Long Cui, Weiyun Wang, Jie Shao, Zichen Wen, Gen Luo, Linfeng Zhang, Yanting Zhang, Yu Qiao, Wenhai Wang
https://arxiv.org/abs/2510.12793

ViCO: A Training Strategy towards Semantic Aware Dynamic High-Resolution
Existing Multimodal Large Language Models (MLLMs) suffer from increased inference costs due to the additional vision tokens introduced by image inputs. In this work, we propose Visual Consistency Learning (ViCO), a novel training algorithm that enables the model to represent images of varying semantic complexities using different numbers of vision tokens. The key idea behind our method is to employ multiple MLP connectors, each with a different image compression ratio, to downsample the vision …

Series B, Episode 12 - The Keeper
BLAKE: Travis! Old man, old man, Lurgen, the healer, did he talk of Star One? Did he speak to you of anything?
OLD MAN: [Virtually inaudible] A fool knows everything and nothing. [Dies]
https://blake.torpidity.net/m/212/518 B7B2

SRUM: Fine-Grained Self-Rewarding for Unified Multimodal Models
Weiyang Jin, Yuwei Niu, Jiaqi Liao, Chengqi Duan, Aoxue Li, Shenghua Gao, Xihui Liu
https://arxiv.org/abs/2510.12784

SRUM: Fine-Grained Self-Rewarding for Unified Multimodal Models
Recently, remarkable progress has been made in Unified Multimodal Models (UMMs), which integrate vision-language generation and understanding capabilities within a single framework. However, a significant gap exists where a model's strong visual understanding often fails to transfer to its visual generation. A model might correctly understand an image based on user instructions, yet be unable to generate a faithful image from text prompts. This phenomenon directly raises a compelling question: …