cs.CV · 2026-10-08 · No. 137

Computer Vision and Pattern Recognition, 2026-10-08.

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

01 — The papers

8 entries
  1. 01

    Never Look Back: Understanding Persistence in 3D Object Memory from Egocentric Videos

    Shravan Chaudhari, William Paul, Suchi Saria, Rama Chellappa, Homanga Bharadhwaj

    cs.CV · cs.AI · cs.RO

    As we move through the world and carry out everyday tasks, we encounter objects that may become relevant only later. We are capable of recalling where we left something or what was inside a container, even without knowing we would need it later. Here, we study how an embodied assistant can build a similar memory from egocentric videos, by observing a person's day-to-day activities. We present Ledger, a persistent 3D object memory that...

    arxiv.org/abs/2610.10538 · PDF

  2. 02

    Rubix: Global Correspondence-Free Point Set Alignment through Assignment Geometry

    Subhransu S. Bhattacharjee, Dylan Campbell, Rahul Shome

    cs.CV · cs.CG · cs.LG · cs.RO · math.OC

    Procrustes-Wasserstein alignment jointly estimates a matching and rotation without supplied correspondences, but alternating minimization can stop at suboptimal solutions. Rubix solves the equally weighted planar problem globally under squared Euclidean loss. Each matching $σ$ of two centered $n$-point sets defines a complex correlation $z_σ=\sum_i\bar x_i y_{σ(i)}$. Their convex hull is the permutation polygon: supporting vertices give...

    arxiv.org/abs/2610.10408 · PDF

  3. 03

    Performance at What Cost? A Sustainability-Aware Performance Index for Cell and Nucleus Instance Segmentation

    Eiram Mahera Sheikh, Alaa Tharwat, Wolfram Schenck

    cs.CV · cs.AI

    Pretrained models for cell and nuclear instance segmentation differ substantially in architecture, pretraining data and objectives, parameter count, inference strategy, adaptation requirements, postprocessing pipeline, and computational demand. Large pretrained and foundation models are increasingly adopted because of their strong zero-shot capabilities, but their use also imposes greater energy consumption, memory requirements, computational...

    arxiv.org/abs/2610.10324 · PDF

  4. 04

    LoomSC: Scalable Deep Subspace Clustering with Projector Factorization and Exact Spectral Reduction

    Nairouz Mrabah, Youssef Melki, Mohamed Bouguessa, Riadh Ksantini, Shakeeb Murtaza, Tehseen Zia

    cs.CV · cs.AI

    Dense self-expression matrices and full-affinity spectral clustering limit the scalability of subspace clustering. We introduce the Latent Orthogonal Optimization Model for Subspace Clustering (LoomSC), a framework that addresses both bottlenecks through projector factorization and exact spectral reduction. Motivated by the spectral structure of least-squares regression, LoomSC jointly learns latent features and a projector...

    arxiv.org/abs/2610.10266 · PDF

  5. 05

    VideoEvolve: Co-Evolving Memory and Retrieval for Long Video Understanding

    Yongchao Xu, Bowen Ye, Jiefeng Gan, Junkai Ma, Wenzhao Li, Sen Tao, Yi Wei, Jiawei Liu

    cs.CV · cs.AI

    Long video understanding increasingly relies on external memory to organize massive visual streams into compact representations. However, most memory-based methods dynamically adapt how information is retrieved for different questions, while largely fixing what is remembered. This mismatch makes missing details costly to recover, whereas stored information is valuable only when it can be reliably retrieved. To address this issue, we propose...

    arxiv.org/abs/2610.10183 · PDF

  6. 06

    From Pixel to Coding: Evaluating the Figure Reproduction Capabilities of MLLMs

    Zijian Chen, Zhengyu Chen, Bohan Liang, Lirong Deng, Yushuo Zheng, Yanwei Jiang, Qi Jia, Kaiwei Zhang, Wenjun Zhang,...

    cs.CV · cs.AI

    Multimodal Large Language Models (MLLMs) have demonstrated impressive capabilities in both visual understanding and code generation. However, existing benchmarks typically evaluate these two modalities in isolation, lacking a dedicated assessment of their unification, i.e., how a model can perceive complex visual structures and synthesize them into precise, executable code. Moreover, current visual code generation benchmarks often rely on...

    arxiv.org/abs/2610.10066 · PDF

  7. 07

    Global Average Precision for Representation Learning

    Bill Psomas, Mohammad Mahdi, Michalis Thomas, Danda Pani Paudel, Giorgos Tolias, Giorgos Kordopatis-Zilos

    cs.CV · cs.LG

    Standard information retrieval metrics, such as mean Average Precision (mAP), assess performance one query at a time, based on how the similarities between a query and its positives compare against those with its negatives. The same holds for common representation learning losses, such as InfoNCE and per-query AP surrogates. None of them considers whether similarities are comparable across queries, which any system with a single decision...

    arxiv.org/abs/2610.09863 · PDF

  8. 08

    DeepTopoClustering: Unsupervised Derivation of Surface Process Taxonomy from 4D Point Clouds for Topographic Monitoring

    Jiapan Wang, Daan Hulskemper, Mathilde Letard, Roderik Lindenbergh, Katharina Anders

    cs.CV · cs.LG

    4D point clouds acquired by permanent laser scanning (PLS) enable accurate high-frequency monitoring of surface change in dynamic topographic environments. However, existing methods remain limited in organizing detected surface activities into meaningful process types. We propose DeepTopoClustering (DTC), an unsupervised framework for deriving a hierarchical process taxonomy from object-based surface activities, so-called 4D objects-by-change...

    arxiv.org/abs/2610.09860 · 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.