Tootfinder

Sample-Aware Test-Time Adaptation for Medical Image-to-Image Translation
Irene Iele, Francesco Di Feola, Valerio Guarrasi, Paolo Soda
https://arxiv.org/abs/2508.00766 https://…

Sample-Aware Test-Time Adaptation for Medical Image-to-Image Translation
Image-to-image translation has emerged as a powerful technique in medical imaging, enabling tasks such as image denoising and cross-modality conversion. However, it suffers from limitations in handling out-of-distribution samples without causing performance degradation. To address this limitation, we propose a novel Test-Time Adaptation (TTA) framework that dynamically adjusts the translation process based on the characteristics of each test sample. Our method introduces a Reconstruction Module…

Test @…!
#RudolfRocker

My non-exhaustive test of @… triggered through @ap.brid.gy bridge between Bluesky and Fediverse has these results:
Bluesky reply to Fediverse post = no joy

Test-time Prompt Refinement for Text-to-Image Models
Mohammad Abdul Hafeez Khan, Yash Jain, Siddhartha Bhattacharyya, Vibhav Vineet
https://arxiv.org/abs/2507.22076 https://

Test-time Prompt Refinement for Text-to-Image Models
Text-to-image (T2I) generation models have made significant strides but still struggle with prompt sensitivity: even minor changes in prompt wording can yield inconsistent or inaccurate outputs. To address this challenge, we introduce a closed-loop, test-time prompt refinement framework that requires no additional training of the underlying T2I model, termed TIR. In our approach, each generation step is followed by a refinement step, where a pretrained multimodal large language model (MLLM) ana…

This fediverse post is designed to test a bot running on Bluesky that can add alt text to images.
This post will have 2 replies, one from the fediverse and one from Bluesky, trying to trigger the bot.
This image in this post does not have alt text included with it by design.
#testing

Replaced article(s) found for cs.CV. https://arxiv.org/list/cs.CV/new
[1/5]:
- Contrastive Test-Time Composition of Multiple LoRA Models for Image Generation
Tuna Han Salih Meral, Enis Simsar, Federico Tombari, Pinar Yanardag

A Hierarchical Test Platform for Vision Language Model (VLM)-Integrated Real-World Autonomous Driving
Yupeng Zhou, Can Cui, Juntong Peng, Zichong Yang, Juanwu Lu, Jitesh H Panchal, Bin Yao, Ziran Wang
https://arxiv.org/abs/2506.14100

A Hierarchical Test Platform for Vision Language Model (VLM)-Integrated Real-World Autonomous Driving
Vision-Language Models (VLMs) have demonstrated notable promise in autonomous driving by offering the potential for multimodal reasoning through pretraining on extensive image-text pairs. However, adapting these models from broad web-scale data to the safety-critical context of driving presents a significant challenge, commonly referred to as domain shift. Existing simulation-based and dataset-driven evaluation methods, although valuable, often fail to capture the full complexity of real-world …

Interesting stuff. This touches on a lot of work that was on my todo list. Especially estimating the "interestingness" of data by measuring the maximum compute needed to reach the optimal compression.
AIT is definitely becoming practically relevant.
https://arxiv.org/abs/2507.07995

Single-pass Adaptive Image Tokenization for Minimum Program Search
According to Algorithmic Information Theory (AIT) -- Intelligent representations compress data into the shortest possible program that can reconstruct its content, exhibiting low Kolmogorov Complexity (KC). In contrast, most visual representation learning systems use fixed-length representations for all inputs, ignoring variations in complexity or familiarity. Recent adaptive tokenization methods address this by allocating variable-length representations but typically require test-time search o…

An Iterative PDE Based Illumination Restoration Scheme for Image Enhancement
Dragos-Patru Covei
https://arxiv.org/abs/2506.12560 https://

An Iterative PDE Based Illumination Restoration Scheme for Image Enhancement
We present a novel iterative scheme for restoring uneven illumination in grayscale images. Our approach solves, at each global iteration, a nonlinear elliptic equation for an auxiliary field $u$ and then updates the illumination via an explicit time-marching step driven by the logarithmic potential of $u$. We establish existence and uniqueness of the discrete subproblems, analyze convergence of the fixed point iteration, and demonstrate performance on standard test images, reporting PSNR and SS…

I replaced my ancient phone with a Fairphone 5 and decided to do the ultimate comparison test: how accurate is the GPS when I'm riding my bike? Answer: on a map the tracks are v close but the F5 is consistently better, fewer wobbles. Errors in location mean errors in distance mean errors in speed: this image shows the new speed readings are much more steady. (NB: all speeds above 25 km/h are downhill.)

Test Roll No. 2 of an Ilford HP4 120, ceased production at 1976, Super Ikonta 533/16, “scanned” by my iPhone
一卷用蔡司超级伊康塔533/16拍摄的Ilford HP4 120, 1976年停产。用iPhone翻拍玩玩，扫描仪扫不了120
#filmphotography #Photography

CNS-Bench: Benchmarking Image Classifier Robustness Under Continuous Nuisance Shifts
Olaf D\"unkel, Artur Jesslen, Jiahao Xie, Christian Theobalt, Christian Rupprecht, Adam Kortylewski
https://arxiv.org/abs/2507.17651

CNS-Bench: Benchmarking Image Classifier Robustness Under Continuous Nuisance Shifts
An important challenge when using computer vision models in the real world is to evaluate their performance in potential out-of-distribution (OOD) scenarios. While simple synthetic corruptions are commonly applied to test OOD robustness, they often fail to capture nuisance shifts that occur in the real world. Recently, diffusion models have been applied to generate realistic images for benchmarking, but they are restricted to binary nuisance shifts. In this work, we introduce CNS-Bench, a Conti…

Single-pass Adaptive Image Tokenization for Minimum Program Search
Shivam Duggal, Sanghyun Byun, William T. Freeman, Antonio Torralba, Phillip Isola
https://arxiv.org/abs/2507.07995

Single-pass Adaptive Image Tokenization for Minimum Program Search
According to Algorithmic Information Theory (AIT) -- Intelligent representations compress data into the shortest possible program that can reconstruct its content, exhibiting low Kolmogorov Complexity (KC). In contrast, most visual representation learning systems use fixed-length representations for all inputs, ignoring variations in complexity or familiarity. Recent adaptive tokenization methods address this by allocating variable-length representations but typically require test-time search o…