Tootfinder

Ok, this is hilarious. https://www.yankodesign.com/2025/06/27/worlds-narrowest-fiat-panda-is-one-anorexic-19-inch-wide-ev-destined-for-the-record-books/

While I'm copying yesterday's photos to my computer, I'll just share some more photos from my recent blog post.
I tried to put the bushes at the lake as framing elements into the #photos. I think it worked out quite okay. -- And while we were on this walk I imagined all the time where and how this could look at sunset or with fog.
Maybe I should go there a again a couple o…

Android 16 kann Smartphone-Nutzer künftig warnen vor möglichen Lauschangriffen
Neue Sicherheitseinstellung in Android 16 warnt vor IMSI-Catchern und unverschlüsselten Verbindungen. Noch unterstützt aber kein Smartphone-Modem die Funktion.

Single-shot HDR using conventional image sensor shutter functions and optical randomization
Xiang Dai, Kyrollos Yanny, Kristina Monakhova, Nicholas Antipa
https://arxiv.org/abs/2506.22426

Single-shot HDR using conventional image sensor shutter functions and optical randomization
High-dynamic-range (HDR) imaging is an essential technique for overcoming the dynamic range limits of image sensors. The classic method relies on multiple exposures, which slows capture time, resulting in motion artifacts when imaging dynamic scenes. Single-shot HDR imaging alleviates this issue by encoding HDR data into a single exposure, then computationally recovering it. Many established methods use strong image priors to recover improperly exposed image detail. These approaches struggle wi…

On the Feasibility of Poisoning Text-to-Image AI Models via Adversarial Mislabeling
Stanley Wu, Ronik Bhaskar, Anna Yoo Jeong Ha, Shawn Shan, Haitao Zheng, Ben Y. Zhao
https://arxiv.org/abs/2506.21874

On the Feasibility of Poisoning Text-to-Image AI Models via Adversarial Mislabeling
Today's text-to-image generative models are trained on millions of images sourced from the Internet, each paired with a detailed caption produced by Vision-Language Models (VLMs). This part of the training pipeline is critical for supplying the models with large volumes of high-quality image-caption pairs during training. However, recent work suggests that VLMs are vulnerable to stealthy adversarial attacks, where adversarial perturbations are added to images to mislead the VLMs into producing …

The SDO HMI - #Sun at 22:41 UTC on 30 May.

Auf einem Band kann man schlecht stehen, sag' ich immer.
https://berlin.social/@karldietzverlag/114770787646460196

Zahlen, bitte! Fünf IBM-Peepshows für herandwachsende Mathematiknerds
Das Ehepaar Ray und Charles Eames waren nicht nur erfolgreiche Architekten, sondern prägten mit sehenswerten Kurz- und Lehrfilmen das Image von IBM.

Gilt für mich in Berlin in jedem Fall auch
From: @…
https://mastodon.no2nd.earth/@WandernAustria/114607052840…

StableCodec: Taming One-Step Diffusion for Extreme Image Compression
Tianyu Zhang, Xin Luo, Li Li, Dong Liu
https://arxiv.org/abs/2506.21977 https://

StableCodec: Taming One-Step Diffusion for Extreme Image Compression
Diffusion-based image compression has shown remarkable potential for achieving ultra-low bitrate coding (less than 0.05 bits per pixel) with high realism, by leveraging the generative priors of large pre-trained text-to-image diffusion models. However, current approaches require a large number of denoising steps at the decoder to generate realistic results under extreme bitrate constraints, limiting their application in real-time compression scenarios. Additionally, these methods often sacrific…