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…

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.

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.

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...…

Apple unveils a 14-inch MacBook Pro with an M5 chip, up to 3.5x more performance for AI workflows, and faster storage, for the same $1,599 , shipping October 22 (Apple)
https://www.apple.com/newsroom/2025/10/apple-unveils-new-14-inch-macbo…

Apple unveils new 14‑inch MacBook Pro powered by the M5 chip, delivering the next big leap in AI for the Mac
Apple today unveiled a new 14-inch MacBook Pro, featuring the incredibly powerful M5 chip.

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…

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…

Apple updates the iPad Pro with an M5 chip, its new C1X cellular modem, and N1 chip, for $999 for the 11-inch and $1,299 for the 13-inch, shipping October 22 (David Pierce/The Verge)
https://www.theverge.com/news/799352/apple-ipad-pro-m5-price-release-date

Apple’s iPad Pro now has an M5 chip and some nice internal upgrades
Last year’s Pro shipped with new accessories, a new deisgn, and a new screen. The 2025 iPad Pro is mostly an internal upgrade, including the new M5 processor.

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…