cs.CV · 2026-09-24 · No. 123

Computer Vision and Pattern Recognition, 2026-09-24.

18 new papers in cs.CV. Titles, authors, abstracts. Links to arXiv. Want this in your inbox every morning? Subscribe →

01 — The papers

18 entries
  1. 01

    On the Diffusibility of High-Dimensional Latents

    Chao Feng, Zhiyang Xu, Bowei Chen, Yuanjun Xiong, Xiyao Wang, Jui-Hsien Wang, Richard Zhang, Zhe Lin, Andrew Owens, Yijun Li

    cs.CV · cs.LG

    Representation Autoencoders (RAEs) enable diffusion models to operate in the feature spaces of pretrained visual encoders. However, many off-the-shelf encoders are not optimized for faithful reconstruction, discarding fine-grained visual details. As expected, finetuning these encoders for image reconstruction recovers such details. However, perhaps counterintuitively, this procedure reduces the effective dimensionality of the resulting...

    arxiv.org/abs/2609.28473 · PDF

  2. 02

    Frozen Flows Forget: Diagnosing and Restoring Lost Motion in a Latent-flow World Model

    Xiwen Chen, Rigaudiere Z. Li, Zhiruo Zhou, Xiaojun Zhu, Houde Liu

    cs.CV · cs.AI · cs.RO

    Latent world models that integrate a flow in a frozen self supervised latent space train stably and cheaply, yet silently lose the property manipulation depends on most: motion. The pretrained flow never moves the manipulated object; retraining it with latent-only losses only trades stillness for teleport-like motion. We trace the failure to the training signal, not the representation: anchor-sparse, latent-only supervision never says where...

    arxiv.org/abs/2609.28414 · PDF

  3. 03

    AnchorReasoning: A Visual Grounding and Causal Reasoning Dataset in Long-Tail Autonomous Driving Scenarios

    Zhipeng Bao, Wenjie Zhao, Tianle Zhu, Haohua Que, Chence Yang, Geng Yuan, Qianwen Li

    cs.CV · cs.AI

    Vision-language models (VLMs) offer a promising approach to long-tail autonomous driving, but existing driving datasets provide limited supervision for connecting decision-critical visual evidence with reasoning and planning. We introduce AnchorReasoning, a visually grounded reasoning dataset built on WOD-E2E, containing 416,119 annotated frames and 395,379 decision-critical elements across four major categories and 19 fine-grained types....

    arxiv.org/abs/2609.28366 · PDF

  4. 04

    PBLH Estimation from Satellite Radiances via a Dual-Encoder Transformer

    Lorenzo Innocenti, Luca Catalano, Edoardo Arnaudo, Claudio Rossi, Salvatore Larosa, Domenico Cimini, Paolo Garza

    cs.CV · cs.LG

    Estimating the Planetary Boundary Layer Height (PBLH) from satellite observations is a challenging regression problem due to the indirect relationship between top-of-atmosphere radiances and near-surface atmospheric structure. Progress has been limited both by the lack of architectures capable of handling the multimodal, spatially incomplete nature of satellite overpasses, and by the scarcity of suitable datasets. In this paper, we build upon...

    arxiv.org/abs/2609.28286 · PDF

  5. 05

    RAMP: Robust Adaptive Mixed-Precision Quantization for Edge CPU Vision Models

    David Población-Criado, Dario Garcia-Gasulla, Eduardo Quinones

    cs.CV · cs.LG · cs.PF

    Deploying deep learning models on edge CPUs is bottlenecked by computational and memory constraints. Mixed-precision quantization promises to reduce inference latency while preserving accuracy. However, quantization affects different layer types in inconsistent ways, so identifying where accuracy loss is minimized and latency reduction is maximized is critical, as the effect accumulates over a full deployment into substantial savings or...

    arxiv.org/abs/2609.28262 · PDF

  6. 06

    Do Center Biases Propagate? Robustness of Pathology Foundation Models in Whole-Slide Image Classification

    Ilán Carretero, Pablo Meseguer, Rocío del Amor, Valery Naranjo

    cs.CV · cs.AI

    Pathology foundation models (PFMs) have transformed computational pathology through powerful representation learning from histopathological images. PFMs provide rich, discriminative representations for whole slide image (WSI) analysis, enabling tasks such as slide-level classification under multiple instance learning (MIL). However, these representations may also encode non-biological signals associated with acquisition centers, potentially...

    arxiv.org/abs/2609.28231 · PDF

  7. 07

    Field-of-View Extension in Dental Cone-Beam CT via Implicit Neural Representations and Diffusion Model-Based Refinement

    Susanne Schaub, Florentin Bieder, Matheus L. Oliveira, Yulan Wang, Buyanbileg Sodnom-ish, Dorothea Dagassan-Berndt,...

    cs.CV · cs.AI

    Dental cone-beam computed tomography (CBCT) systems often employ detector configurations that provide a truncated field of view (FOV) that only captures a small part of the patient's anatomy. In this work, we aim to reconstruct an extended FOV using projections of truncated FOV scans. To this end, we propose a three-stage framework that consists of (1) an implicit neural representation (INR) for estimating missing parts of the truncated...

    arxiv.org/abs/2609.28110 · PDF

  8. 08

    Visual Tripwires: Anticipating Failure in Deep Vision Systems

    Anoushka Harit, Rehan Zuberi, William Prew, Florian Markowetz

    cs.CV · cs.LG

    Deep vision systems remain vulnerable to corruption, occlusion, and distribution shift despite strong benchmark performance. Existing reliability methods typically evaluate uncertainty at individual time steps and do not explicitly model how a system progresses toward failure. We introduce Visual Tripwires, a predictive reliability framework that uses temporal instability in model behaviour to anticipate impending failure. Our central...

    arxiv.org/abs/2609.28099 · PDF

  9. 09

    Prompt, Probe, Train, or Annotate? Single-camera sports video understanding in amateur settings

    Sai Varun Kodathala, Prashanth Pollishetty, Jaylen Cargill

    cs.CV · cs.AI

    Video understanding is usually benchmarked on curated, single-actor, or professionally filmed clips, and a strong score there is routinely read as evidence a model is robust enough for deployment. Amateur team sport is a useful, largely untested place to check that assumption: over eight million students played a school sport in the United States in 2024-25 alone, almost none of it filmed by more than a single fixed camera, with several...

    arxiv.org/abs/2609.28049 · PDF

  10. 10

    Task-Induced Riemannian Metrics for Vision Transformer Feature Spaces

    Andrew Bond, Ege Erdem Özlü, Tuna Çimen, Ilkin Umut Melanlioglu, Tolga Birdal, Erkut Erdem, Aykut Erdem

    cs.CV · cs.LG

    Methods operating on Vision Transformer (ViT) feature spaces typically rely on Euclidean distance or cosine similarity. This assumes that every direction is equally meaningful, but there is no reason to believe the true task geometry has this property. The task-sensitive geometry of the feature space is given by the pullback metric $g(F) = J(F)^\top J(F)$, where $J$ is the Jacobian of the decoder's output fed to a task-specific distance, with...

    arxiv.org/abs/2609.27988 · PDF

  11. 11

    FFM-CP: Cross-Backbone Fusion of Vision-Language Foundation Models for Few-Shot Computational Pathology

    Anh-Tien Nguyen, Trung DQ. Dang, Nghiem Tuong Diep, Bui Ngoc Han Nguyen, Tan-Ha Mai, Miriam Cindy Maurer, Phuong Hoa...

    cs.CV · cs.LG

    Pathology vision-language foundation models vary in performance across diseases and tasks, with no single model consistently performing best. The high cost of expert pathology annotation can also limit the labeled data available for task-specific adaptation. Combining complementary pretrained representations is a potential approach to these limitations, yet learning an effective fusion from few labeled examples remains challenging. We...

    arxiv.org/abs/2609.27710 · PDF

  12. 12

    InGuard: Towards Generalized Inner Guardrail for Safe Text-to-Image Generation

    Zeyu Wang, Xiaodan Li, Zhiwen Li, Yuefeng Chen, Hui Xue

    cs.CV · cs.AI

    Modern text-to-image (T2I) models generate high-quality images from arbitrary user prompts, yet they can just as easily produce not-safe-for-work (NSFW) content. Conventional outer guardrails consist of two components: a prompt classifier that checks for risk before generation, and a post-hoc image classifier that checks the fully generated image. In this design, both classifiers operate outside the generation pipeline and do not use the...

    arxiv.org/abs/2609.27620 · PDF

  13. 13

    M3D-Net: Hierarchical Coordination of Spatial Context, Feature Reuse, and Differential Attention for Mammography Classification

    Zheng Yu, Xinhang Li, Jiabao Gao, Boyang Wang, Xiang Li

    cs.CV · cs.LG

    Breast image classification requires local detail and global tissue context, yet these cues can weaken as representations deepen. We present M3D-Net, a mammography encoder that hierarchically coordinates multi-scale coordinate attention, bounded dynamic feature reuse, and differential attention through resolution-aware operator placement. Within-stage retrieval preserves access to earlier features, coordinate-aware aggregation integrates...

    arxiv.org/abs/2609.27523 · PDF

  14. 14

    NV-Reason-CT: 3D Visual Language Model for CT Analysis

    Andriy Myronenko, Dong Yang, Yucheng Tang, Baris Turkbey, Benjamin Simon, Stephanie Harmon, Rikhil Makwana, Mariam...

    cs.CV · cs.AI

    We present NV-Reason-CT, a generative vision--language model for chest and abdominal CT combining native 3D visual encoding with radiologist-guided reasoning. The model couples a native 3D vision transformer with a language model, passing all visual tokens and their explicit 3D coordinates into language decoding without further spatial token merging. This retains volumetric spatial information within the vision encoder and through the...

    arxiv.org/abs/2609.27511 · PDF

  15. 15

    DeltaS: Reading the Gated Linear Attention State for KV Cache Eviction in Streaming Video

    Taeyoun Kwon, Seungjin Kim, Hyeonyu Kim, Moon Hwan Kim

    cs.CV · cs.CL · cs.LG

    Recent video-language models increasingly adopt hybrid architectures that interleave linear and full attention layers for efficient long-context processing. While the recurrent state of linear attention remains fixed in size, the KV cache of full attention continues to grow with the video stream, making eviction necessary under a bounded memory budget. The key challenge in streaming is that eviction must occur before the question arrives, so...

    arxiv.org/abs/2609.27470 · PDF

  16. 16

    What Looks Like a Capability Limit in Vision-Language Models Is a Readout Limit

    Alfredo F. Frontera Del Valle

    cs.CV · cs.AI · cs.CL

    Benchmarks for vision-language models offer their answer choices in some convention: a letter, a color name, a pixel coordinate. That convention is treated as neutral. We find it is not, and that the limits a benchmark reports can belong to the readout rather than to the model. On 200 COCO photographs, Qwen3-VL-4B picks the correct one of nine locations for a named object 68.5% of the time when the locations are given in English and 20.0%...

    arxiv.org/abs/2609.27408 · PDF

  17. 17

    Geometry-Conditioned Visual Place Recognition in Natural Environments

    Walter Nedov, Saimunur Rahman, Kavindie Katuwandeniya, David Hall, Kaushik Roy, Peyman Moghadam

    cs.CV · cs.AI · cs.RO

    Visual Place Recognition (VPR) in natural environments remains challenging due to repetitive vegetation, sparse distinctive landmarks, and substantial appearance and viewpoint variation across traversals. While visual observations of the same place can change considerably, their underlying spatial structure is often more persistent. We exploit this complementary geometric consistency through Depth-Aware Distillation (DAD), which conditions...

    arxiv.org/abs/2609.27370 · PDF

  18. 18

    Breaking Weather-Content Coupling: Type-Severity Guided Progressive Disentanglement for All-in-One Infrared Restoration

    Xinyao Wang, Lijun He, Zhihan Ren, Fan Li

    cs.CV · cs.AI

    Infrared (IR) imaging is crucial for autonomous driving, remote sensing, and other perception tasks. However, adverse weather may introduce fake structural responses that are entangled with real thermal structures. Existing IR restoration methods are typically designed for a single degradation type or directly reconstruct from degradation-entangled representations. Consequently, they struggle to distinguish intrinsic thermal structures from...

    arxiv.org/abs/2609.27317 · PDF

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.

Colophon Set in Georgia, with system sans for interface chrome and a monospaced stack for code and paper identifiers. Sole accent: amber #D99C5E. Built and served on an always-free VM. The masthead is set 14% letterspaced because newspapers do that and it works.