cs.CV · 2026-11-10 · No. 169
Computer Vision and Pattern Recognition, 2026-11-10.
12 new papers in cs.CV. Titles, authors,
abstracts. Links to arXiv. Want this in your inbox every morning? Subscribe →
01 — The papers
12 entries-
01
What kills $v$-prediction? A Patch-wise PCA Perspective on Pixel-Space Flow Matching
Tianze Luo, Haofeng Huang, Yuan Yao
cs.CV · cs.LG
Latent Diffusion Models dominate generative modeling but face two-stage training complexity and the inherent reconstruction limits of pre-trained autoencoders. Pixel-space Flow Matching offers a simplified end-to-end alternative yet often encounters training difficulties when using the standard $v$-prediction objective. Recent research attributes this difficulty to the off-manifold nature of noised targets, motivating a shift toward...
-
02
2D Gum-Net: Unsupervised Dense Elastic Image Registration via Symmetric Correlation and Spectral Pooling
Aarya Bhave, Anushka Ajay Bhave
cs.CV · cs.AI
Dense non-rigid registration, the recovery of a pixel-wise deformation field that warps one image into geometric agreement with another, is fundamental across medical imaging, structural biology, and correspondence estimation, yet learning-based approaches face a severe bottleneck: ground-truth deformation fields are notoriously difficult to obtain for real data. We present 2D Gum-Net, an end-to-end architecture that predicts dense elastic...
-
03
OptiCover: A Scalable and Multi-Surface Framework for Cold-Start Visual Optimization under Semantic Constraints
Guillaume Guy, Mihajlo Grbovic, Joe Mills, Selen Uguroglu, Liwei He, Pratiksha Kadam, Nalini Kartha, Qian Aria Li
cs.CV · cs.LG
Selecting an effective cover photo is a critical yet understudied problem in visual merchandising for e-commerce marketplaces. On Airbnb, hosts upload many photos depicting different rooms, amenities, and points of interest, but must manually choose a single static cover photo that is reused across heterogeneous product surfaces. This creates substantial challenges: over 90\% of listing photos have no engagement labels, leading to a severe...
-
04
GeoScope: Training-Free Program Execution beyond the Counting Horizon for Ultra-High-Resolution Remote Sensing Question Answering
Guohui Deng, Yuhang Jiang, Chengjun Wang, Zhongwen Hu, Zhaocong Wu, Linsheng Huang, Jinling Zhao, Chao Ruan,...
cs.CV · cs.AI
In ultra-high-resolution (UHR) remote sensing images, the objects that questions count in a region or relate by direction often span only a few pixels. Existing methods mainly decide where a vision-language model (VLM) should look and trust its answer in the chosen view. We show that this assumption fails for counting, and measure VLMs as one calibrates a sensor. All eight open VLMs tested fall increasingly short once a view holds more than a...
-
05
Evaluating Cross-Signal Coherence in Mammography Vision-Language Models
Rebeca Nam, Chase M. Fensore, Christian A. Fauria-Robinson, Judy Gichoya, Joyce C. Ho
cs.CV · cs.CL · cs.LG
As vision-language models (VLMs) move toward interpreting medical images directly, their outputs increasingly include not just a label but a stated confidence and a written justification. Yet the field still predominantly evaluates VLMs using just accuracy. We evaluate the coherence between answer, confidence, and explanation across four VLMs on breast density and BI-RADS categorization, using two mammography datasets. We perform controlled...
-
06
WanderBench: Can World Models Explore Dynamic Worlds from Video?
Yuhang Chen, Jiheng Li, Jiale Wang, Zai Wang, Guangyue Liu
cs.CV · cs.AI
Video world models conditioned on an input video make it possible to explore real, recorded dynamic scenes, enabling re-shooting of footage, free-viewpoint replay, and real-to-sim environments for embodied agents. Such uses require the generated rollout to stay faithful to the recorded world, yet existing benchmarks start from a single image or a text prompt, and video-conditioned generation is evaluated mainly on perceptual quality and...
-
07
MARS: Multiscale Appearance-Residual Streams for Video Forgery Detection
Ahmed Y. Radwan, Shaina Raza
cs.CV · cs.AI
Generalizing deepfake detection across facial manipulation and fully generated video remains challenging due to forgery traces varying with the manipulation method and scene content. Explicit spatial and temporal feature differences offer a way to capture this variation, but also respond to natural texture and motion, motivating their joint interpretation with appearance features. We investigate whether combining multiscale feature...
-
08
dNaViT: Discrete Codes are General-Purpose Visual Representations
Xiaotong Li, Zhengrong Yue, Xu Huang, Jialv Zou, Minhao Jing, Wenhao Yan, Haodong Li, Hai Huang, Bo Zhao, Yan Feng,...
cs.CV · cs.AI
Discrete autoregressive modeling, notably through next-token prediction, has become a cornerstone of modern language models. Extending this paradigm to vision allows visual and language models to converge on a unified framework, thereby fostering shared methodology and infrastructure. This work investigates a central question: how far can a finite discrete vocabulary go in representing the richness of the visual world? We present dNaViT, a...
-
09
HumanSightBench: A Benchmark for Human Visual Perception in MLLMs
Zixin Su, Yangguang Lin, Zegang Peng, Yuntong Sun, Xuanyi Wang, Jiahao Wang, Qiankai Xu, Bing Yuan, Jinze Bai,...
cs.CV · cs.AI · cs.CL
Multimodal large language models (MLLMs) have demonstrated strong performance on knowledge-intensive and reasoning-based vision-language benchmark datasets, but still struggle to solve the visual questions that people can solve easily. Evaluating the differences between MLLMs and human-level visual perception is challenging due to end-to-end evaluation which combines various skills, or because we are uncertain if individual items are valid....
-
10
CADMA: Capacity-Aware Coverage Decomposition for Generative Model Assessment
Debin Meng, Zheng Gao, Ziquan Liu, Yanran Li, Ioannis Patras, Georgios Tzimiropoulos
cs.CV · cs.LG
Evaluating generative models requires measuring not only sample fidelity but also how well a generated set covers the real data distribution. Recent work has therefore introduced recall-oriented metrics for distribution-level evaluation. However, existing recall metrics often reduce distributional coverage to geometry-based coverage. This simplifying assumption weakens their diagnostic value and interpretability in two ways: these metrics...
-
11
How a Model's Architecture and Performance Influences Explainability: A Study of Grad-CAM and CRAFT in CNN-Based Image Classification
Kilian Göller, Haadia Amjad, Steffen Seitz, Carsten Knoll, Ronald Tetzlaff
cs.CV · cs.AI
Deep learning models, particularly convolutional neural networks (CNNs), are widely adopted in computer vision, yet their opaque decision-making raises concerns in high-risk applications like healthcare and autonomous systems, where trust and accountability are critical. Therefore, robust explainable AI (XAI) methods are desirable to provide transparent insights into model decisions. To ensure these methods are reliable and effective across...
-
12
Leveraging Complementary Event Frame and Voxel Representations for RGB-Guided Multimodal Pre-training
Wentao Wu, Xiao Wang, Yi Wang, Chenglong Li, Yonghong Tian, Bin Luo
cs.CV · cs.AI
In this paper, we propose CM3AE 2.0, a unified RGB Frame and Event-Voxel/-Frame pre-training framework. By jointly learning multimodal spatiotemporal representations and exploiting latent cross-modal dependencies through cross-modal generation, the framework enhances multimodal information interaction and collaborative modeling capabilities. Specifically, we first propose an Event-aware Spatiotemporal Masked Reconstruction (ESMR) strategy to...
This edition is part of The Daily Abstract — cs.CV archive. Subscribe to receive these in your inbox each morning, automatically translated to Spanish, with reply-to-PDF: arxivdaily.ignorelist.com.
#D99C5E. Built and served on an always-free VM. The masthead is set 14% letterspaced because newspapers do that and it works.