cs.CV · 2026-10-14 · No. 143
Computer Vision and Pattern Recognition, 2026-10-14.
22 new papers in cs.CV. Titles, authors,
abstracts. Links to arXiv. Want this in your inbox every morning? Subscribe →
01 — The papers
22 entries-
01
Cepheid: Decoupling Scale from Structure for Cross-Family Motion Completion
Chih-Hai Su, Tsung-Wei Ke, Yu-Lun Liu
cs.CV · cs.GR · cs.LG
Sparse-to-dense motion completion recovers dense mesh motion from sparse vertex displacements. Residual priors trained on one geometry family frequently fail to beat parameter-free harmonic extension off-family. Moreover, cross-family training meets a scaling barrier: residual amplitude varies by more than an order of magnitude across geometry families and collapses as observations become denser. Since this scale depends on unknown target...
-
02
Registration is a Representation Problem: Solving Whole-Body PET/CT Registration
Neel Dey, Adrian V. Dalca
cs.CV · cs.LG
Raw image intensities are a poor surrogate for similarity across images in correspondence problems. Further, while auxiliary segmentation labels can provide semantic identification and improve matching, they can assign only coarse identities to fine-grained anatomy and often cover only a subset of structures, particularly in whole-body settings. We present an approach that instead establishes correspondence using complementary representations...
-
03
AIRRI: Towards a Human-Readable, Machine-Resistant Reading Interface
Emory Salaun, Syed Ayon, Kaleel Mahmood, Shaun Wallace
cs.CV · cs.HC · cs.LG
The rapid advancement of image-to-text extraction systems and large language models (LLMs) poses new challenges for educational assessment by making assignment materials easy to transcribe and solve with minimal human effort. To address this problem, we present AIRRI (Artificial Intelligence Resilient Reading Interface), a framework for generating machine-resistant educational content, a dataset of higher-education assignments for evaluation,...
-
04
GeoReader: Learning Latent Geometry for Spatial Reasoning in Vision-Language Models
Rong Li, Shijie Li, Jiangyong Huang, Lingdong Kong, Jiaming Zhou, Dongyue Lu, Zeying Gong, Baoxiong Jia, Junwei...
cs.CV · cs.AI · cs.LG · cs.MM
Vision-language models (VLMs) struggle with metric and multi-view relationships that remain implicit in RGB observations. Geometry foundation models recover this structure from RGB, but existing methods either fuse the estimated features with visual tokens and learn to use them from question answering alone, or align VLM latents with geometry features. Capturing geometry, however, does not ensure its use: zeroing the aligned latents of a...
-
05
Just Respect the Semantics: Image-Token Compression via Pre-LLM Semantic Variable-Resolution Tokenization and In-LLM Relevance Pruning
Tianhao Fu, Austin Wang, Charles Chen, Roby Aldave-Garza, Victor Xie, Xiyue Jiao, Yucheng Chen, Martin Tin
cs.CV · cs.AI · cs.LG
Image-token compression must reduce computation without hurting the semantics. We introduce Varest, guided by semantic fungibility: tokens within a coherent semantic region can be summarized coarsely, while object boundaries and literal text require finer distinctions. Object and text localizers guide variable-resolution merging, preserving spatial coverage and finer detail at boundaries and text. Learned [REL] registers then prune visual...
-
06
RadarGSOcc: Doppler-Aware 3D Semantic Occupancy Prediction Using 4D Radar Tensor with Geometric-Semantic Feature Extraction
Christofel Rio Goenawan, Dong-Hee Paek, Seung-Hyun Kong
cs.CV · cs.AI · cs.RO
3D semantic occupancy prediction is crucial for autonomous driving, but camera-based methods degrade in low-light conditions and LiDAR-based methods are sensitive to adverse weather. 4D radar is more robust, yet its sparsity and the high cost of radar tensor processing limit its use. We propose Radar Geometric-Semantic Occupancy Prediction (RadarGSOcc), an efficient framework that directly processes 4D radar tensors by separately extracting...
-
07
Texture Interpolation as Texton Matching
Ido Madar, Gal Oren, Shai Avidan
cs.CV · cs.GR · cs.LG
Texture interpolation asks what should lie between two textures. Standard methods typically blend pixels or features at corresponding spatial locations, implicitly assuming that co-located elements should be mixed. For unrelated textures, however, this correspondence is arbitrary: a crack at one location has no particular relationship to a fiber at the same location in another image. We study whether this hidden pairing choice is itself a...
-
08
ST-GRU PredRNN-V2: A GRU-Based Reformulation of PredRNN-V2 for Video Prediction
Augusta van Haren, Hanna Hoogen, Luca Pattavina, Quincy Rommen
cs.CV · cs.AI
Video prediction requires models to capture complex spatiotemporal dependencies and to retain relevant information over long sequences. PredRNN and its successor PredRNN-V2 address this challenge with spatiotemporal Long Short-Term Memory (ST-LSTM) units that maintain two separate memory states, at the cost of a relatively complex recurrent building block. In this work, we investigate whether the simpler gating of Gated Recurrent Units (GRUs)...
-
09
MajorTOM:Elliot Pretrain, A Multi-Sensor, Multi-Temporal Pretraining Dataset for Earth Observation
Carmen Oliver Huidobro, Mikolaj Czerkawski, Kevin Monsalvez-Pozo, Cesar Aybar, Gustau Camps-Valls, Oscar J. Pellicer-Valero
cs.CV · cs.LG
Pretraining generalist Earth observation foundation models requires data that combine several sensors, varied temporal sampling and, increasingly, text, yet open datasets rarely provide all three in one consistent, easily accessible form. We introduce MajorTOM:Elliot Pretrain, a collection of 279,166 tiles of 10 km drawn from the Major-TOM grid by clustering AlphaEarth embeddings. Each tile stacks Sentinel-2 L1C, Landsat-8/9, Sentinel-1 RTC,...
-
10
LLM2R: From Large Language Models to 3D Reassemblers
Zhouhan Zhong, Qiuhong Shen, Xingyi Yang, Jinyi Xu, Xinchao Wang
cs.CV · cs.AI · cs.RO
3D part assembly aims to reconstruct a complete shape from a set of unassembled parts by predicting a rigid SE(3) transformation for each part. Because the placement of a part is rarely determined by its own geometry, the task demands reasoning over the entire part set, and existing methods, which rely on pairwise relations or iterative generation and verification, scale poorly to objects with many parts. We present LLM2R, which casts part...
-
11
Rethinking Projector Training in Multimodal LLMs
Fabian Gröger, Naël Ouerghemi, Shuo Wen, Maria Brbić
cs.CV · cs.AI · cs.CL
Multimodal LLMs are typically trained by first aligning a vision encoder with a language model via projector training on large image-caption datasets, followed by joint training of the full multimodal model. Despite its widespread use, the role of the projector training stage remains poorly understood. We find that (i) using only $10$ to $20\%$ of the data for training the projector already recovers most downstream performance gains, and (ii)...
-
12
Beyond the Encoder: Object-Centric Representations Emerging from Segmentation Foundation Models
Michalis Pistos, Bartłomiej W. Papież
cs.CV · cs.LG
Foundation models are increasingly used as feature extractors for downstream tasks with limited data, typically through representations obtained from their encoders. However, foundation models trained for structured tasks such as segmentation also form object-specific representations during task execution, whose transferability remains largely unexplored. We investigate Segment Anything Model 2 (SAM2) object pointers, compact object-level...
-
13
EgoOmniWorld: Unifying Egocentric Understanding via Ego-Action-World Interactions
Songruo Chen, Yuqian Fu, Yu Li, Mingkang Dong, Sifan Zhou, Bin Ren, Xu Zheng, Tianwen Qian, Mohamed Elhoseiny, Yanwei Fu
cs.CV · cs.AI
Egocentric video understanding spans diverse capabilities, modalities, and evaluation formats, yet these are often studied in isolation despite their tight coupling in real-world interaction. We propose the Ego-Action-World interaction loop as a unifying principle: the wearer perceives the world, forms goals, acts, changes the world, and uses feedback to guide subsequent behavior. Based on this view, we introduce EgoOmniWorld, a benchmark...
-
14
Simplifying and Improving On-Policy Distillation for Few-Step Diffusion
Jiawei Zhang, Ziyu Wan, Nanye Ma, Long Zhao, Dong Chen, Hongyu Liu, Qifeng Chen, Dongdong Chen
cs.CV · cs.LG · eess.IV
Few-step distillation reduces the sampling cost of diffusion and flow models, but existing approaches often require auxiliary score models or specialized architectures. We show that simple on-policy velocity regression already provides a strong foundation for 4-NFE generation. To represent teacher velocity variation within each coarse transition, we introduce Pivot, a training-only residual proxy that separates local corrections from the...
-
15
Resource-Efficient 3D Shape and Orientation Estimation of Road Users using Roadside RGB Camera and 3D Radar
Shiva Agrawal, Savankumar Bhanderi, Gordon Elger
cs.CV · cs.AI
End-to-end deep learning pipelines for camera-radar 3D object detection are well established in driver assistance systems and autonomous vehicles; however, adapting them to roadside-mounted infrastructure presents significant challenges. On vehicles, sensor heights, pitch angles, and relative geometries remain largely uniform, allowing end-to-end models to generalize effectively. On the contrary, roadside sensor installations vary drastically...
-
16
Urbex: Agentic Spatial Grounding for City-Scale 3D Scenes
Yu Wang, Rui Dai, Wei Chen, Yi Wang, Bo Dang, Kaikui Liu, Xiangxiang Chu, Yansheng Li
cs.CV · cs.AI
City-scale 3D grounding is commonly formulated as candidate ranking, which requires precomputed instance proposals and becomes inefficient in large outdoor scenes. We propose Urbex, an agentic vision-language framework that instead casts grounding as active spatial search. Urbex represents a city-scale 3D scene as an interactive multi-view environment, allowing a VLM agent to query landmarks, zoom into local regions, render oblique views, and...
-
17
ShoeFit: A New Dataset and Dual-image-stream DiT Framework for Virtual Footwear Try-On
Yuhan Li, Zhiyu Jin, Yifan Tong, Wenxiang Shang, Benlei Cui, Xuanhong Chen, Hangcheng Zhu, Bingbing Ni
cs.CV · cs.AI
Virtual footwear try-on (VFTON), a critical yet underexplored area in virtual try-on (VTON), aims to synthesize faithful try-on results given diverse footwear and model images while maintaining 3D consistency and texture authenticity. Unlike conventional garment-focused VTON methods, VFTON presents unique challenges due to (1) Data Scarcity, which arises from the difficulty of perfectly matching product shoes with models wearing the identical...
-
18
AffectWorld: Benchmarking Emotion-Driven Future World Prediction
Changhao Song, Yacong Chen, Hui Gao, Yazhou Zhang, Peng Zhang
cs.CV · cs.AI
The world encompasses both physical environments and human actors. Predicting its evolution requires understanding both physical laws and how emotions shape human actions. However, existing world model benchmarks primarily assess physical plausibility and perceptual quality, leaving emotion-driven world evolution largely untested.We introduce AffectWorld, a benchmark that evaluates the chain Emotion-Action-World State through three tasks:...
-
19
Robust Logical Anomaly Detection under Capture Shifts via Synthetic Anomalies
Ufuk Efe, Alptekin Temizel
cs.CV · cs.LG
Detectors of logical anomalies, such as missing, extra or wrongly combined parts, usually score a test image by its distance from normal (good) images. They achieve near-perfect image-level AUROC on standard industrial anomaly detection benchmarks such as MVTec LOCO, but their robustness to changes in capture conditions remains largely unexamined. Under a heterogeneous perturbation protocol in which each test image is randomly kept unaltered...
-
20
FALLNEST: Dual-Domain Dataset Condensation of Imbalanced IMU Data for Wearable Fall Detection
Rashi Niyas P, Ritika Jain, Hitika Tiwari
cs.CV · cs.AI · eess.SP
Wearable fall detection is hampered by rare fall events, scarce labeled IMU data, and the cost of training deep models on large, imbalanced corpora. Existing methods either rely on hand-crafted features with shallow classifiers, which limits learning from raw signals, or train deep networks on full datasets that require re-sampling to counter class skew and demand substantial data and compute. To address this, we propose a novel Fall...
-
21
LiFUSE: Frequency-Spatial Unified Self-Supervised Pretraining for Liver Disease Analysis on Non-contrast CT
Hao Zhang, Yi Huang, Wei Liu, Yuan Gao, Zeju Li, Xu Han, Yu Shi, Ling Zhang, Ke Yan
cs.CV · cs.AI · cs.LG
Given the growing global burden of liver tumors and diffuse liver diseases, non-contrast computed tomography (NCCT) is increasingly used for opportunistic screening because of its low cost and favorable safety profile. However, downstream tasks such as tumor detection and fine-grained disease diagnosis remain challenging due to NCCT's inherently low tissue contrast, lack of hemodynamic enhancement, and complex anatomical background. These...
-
22
Heading Hierarchy Reconstruction for Complex and Long Documents with Level-Wise Multimodal Memory
Qian Chen, Xianyin Zhang, Lifan Guo, Chi Zhang
cs.CV · cs.AI
Vision-language models (VLMs) have been widely adopted for document parsing and optical character recognition (OCR), as they can accurately extract page-level elements. However, downstream applications such as retrieval-augmented generation (RAG) also require coherent document-level structure. Although these models indicate heading levels using different numbers of preceding ``\#'' symbols, page-by-page prediction often lacks document-level...
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.