cs.CV · 2026-10-27 · No. 155
Computer Vision and Pattern Recognition, 2026-10-27.
13 new papers in cs.CV. Titles, authors,
abstracts. Links to arXiv. Want this in your inbox every morning? Subscribe →
01 — The papers
13 entries-
01
Does VGGT Know What It Does Not Know?
Adityan Thirumani Srinivasan, David Nordström
cs.CV · cs.LG
Feed-forward 3D reconstruction models such as VGGT regress cameras and geometry in a single forward pass, but they report no uncertainty for the camera poses they predict: an incorrect relative pose looks no different from a correct one. We ask whether the frozen model nonetheless knows when its pose is wrong. On HardMatch, a benchmark of 1,000 deliberately difficult image pairs on which VGGT fails on 35% of pairs, a linear probe on VGGT's...
-
02
OmniShowcase: Omnidirectional Subject-Consistent Video Generation from Multi-View Images
Junyeong Ahn, Geonwoo Kim, Kinam Kim, Gihwi Kim, Hoonjin Jung, Hyojin Jang, Jaegul Choo
cs.CV · cs.AI
Generating videos of a specific subject from a few reference images remains challenging when the camera reveals surfaces that are not visible in the input. Early subject-to-video (S2V) methods condition on a single reference image and must therefore infer the subject's unseen appearance and geometry as the viewpoint changes. To address this limitation, recent methods extend S2V to multiple reference views, providing more information about the...
-
03
Generative Structure from Motion with Native 3D Diffusion
Haobin Duan, Binbin Huang, Mochu Xiang, Yiqun Zhao, Zibo Zhao, Yi Ma, Shenghua Gao
cs.CV · cs.AI
Recovering an object's 3D structure and camera motion from a few uncalibrated views is a fundamental problem in computer vision. Classical structure from motion methods recover 3D geometry consistent with the input images but cannot recover unseen regions; native generation methods produce plausible 3D objects which are related but not necessarily faithful to the input images. Methods simply concatenating reconstruction and generation allow...
-
04
ACSAN: All-Convolutional Self-Attention Network Integrating Convolutional Operations with Vision Transformer
Zimian Wei, Tianqi Zhang, Hengyue Pan
cs.CV · cs.AI
In the past few years, Vision Transformer (ViT) has achieved excellent performance in the field of computer vision. However, there still some problems remain. For instance, ViTs heavily rely on large-scale training data since they simply contain a large number of trainable parameters, which slows down their learning efficiency and limits their applicability in resource-constrained scenarios. In this paper, we propose a novel deep learning...
-
05
Shared-Factor-Conditioned Diffusion for Low-Rank Tensor Recovery
Zhengyun Cheng, Guanwen Zhang, Wei Zhou
cs.CV · cs.AI
Tensor recovery spans heterogeneous data structures and observation processes, calling for a representation that can adapt across modalities and tasks. We propose DiffTR, an unsupervised framework that unifies tensor completion, denoising, and hyperspectral super-resolution through coordinate-conditioned diffusion. Shared factors indexed by tensor coordinates condition a compact score network, and score matching jointly learns the factors and...
-
06
Targeted Deep Regression - Initial Applications in Whole-Body Water-Fat MRI in UK Biobank
Filip Marttala, Taro Langner, Johan Öfverstedt, Nouman Ahmad, Håkan Ahlström, Robin Strand, Joel Kullberg
cs.CV · cs.LG
UK Biobank is a British clinical study which, in addition to large amounts of medical data collected, plans to include detailed Magnetic Resonance Imaging (MRI) examina- tions from 100,000 participants. The image data can be analyzed for example by auto- mated analysis with neural networks for image segmentation or classification to expand the collection of image-derived phenotypes for medical research. In this work, we pro- pose, present and...
-
07
Beyond Vision-Language Models: Visual-Semantic Affect Graphs for Emotion Recognition in Artworks
Ngoc-Duy Mai, Ha-Thanh Nguyen, Hideaki Takeda
cs.CV · cs.AI · cs.CL · cs.LG
Emotion recognition in artworks remains challenging because affective meaning is often subjective, implicit, and shaped by relationships between visual form and semantic associations. While vision-language models provide strong multimodal representations, direct image-to-emotion prediction may overlook explicit relations among formal, semantic, and affective cues that support emotional interpretation. This paper proposes Visual-Semantic...
-
08
Reading Beyond OCR Noise: Robust Cross-Lingual RAG for Legislative Archives
Radha Krishna Deshpande, Ajoy Mondal, Akash Manna, C V Jawahar
cs.CV · cs.AI · cs.IR
India's historical public archives present severe computer vision and document image analysis challenges: decades of parliamentary records survive only as degraded, multi-column scanned pages featuring mixed scripts, complex layouts, and dense visual noise where OCR failure is the primary obstacle to information retrieval. We present an end-to-end framework that couples vision-based layout segmentation and multi-script OCR with an agentic...
-
09
Joint Latent Reasoning and Observation for Agentic Video Understanding
Junzhang Liu, Hao Yuan, Qi Zhang, Yiming Wu, Long Chen, Zhecan Wang
cs.CV · cs.AI
Effective video agents must learn not only how to answer, but also where to look next. Transferring this capability to smaller models is challenging because each observation serves two purposes: supporting an answer and guiding the search for further evidence. Textual descriptions may capture what is currently visible while omitting cues needed for subsequent acquisition. We introduce Latent Agentic Reasoning for Video Analysis (LARVA), a...
-
10
OrthoRF: Exploring Orthogonality in Object-Centric Representations
Despoina Touska, Bastiaan Onne Fagginger Auer, Alexandru Onose, Tejaswi Kasarla, Luis Armando Pérez Rey, Maximilian...
cs.CV · cs.AI · cs.LG
Neural synchrony is hypothesized to help the brain organize visual scenes into structured multi-object representations. In machine learning, synchrony-based models analogously learn object-centric representations by storing binding in the phase of complex-valued features. Rotating Features (RF) instantiate this idea with vector-valued activations, encoding object presence in magnitudes and affiliation in orientations. We propose Orthogonal...
-
11
Uncertainty Evaluation to Support Safety of the Intended Functionality Analysis for Determining the Applicability of Performance Targets Across Triggering Conditions in ML-Based LiDAR Object Detection
Milin Patel, Rolf Jung
cs.CV · cs.LG · cs.RO
For safety of the intended functionality (SOTIF) analysis according to ISO 21448, a machine learning object detector for light detection and ranging (LiDAR) point clouds can meet a performance target, a limit on the mean per-frame share of wrong detections among accepted detections, by rejecting detections above an uncertainty threshold. A threshold selected on data of one condition carries a statistical guarantee only for data distributed...
-
12
Improving VLMs on Scientific Chart Analysis via Autonomous Evolution
Abhinav Sudhakar Dubey, Vidushi Goel, Kiran Rana, Shikhar Mathur, Vaggos Chatziafratis
cs.CV · cs.CL · cs.LG
Understanding and operating with scientific charts is a standard approach in data analysis, and while humans are good at interpreting such charts, open vision-language models (VLMs) are known to perform poorly when it comes to question answering based on such data types. Motivated by an initial observation that many of their errors are due to inexact answering, we raise the following natural question: how much accuracy can we recover without...
-
13
Blendshape Generation for Models with Disconnected Parts: Adding ARKit/MediaPipe Blendshapes to Anime-Style Character Models
Pramook Khungurn
cs.CV · cs.GR · cs.LG
Blendshape generation for 3D models has been extensively researched, but very few works address generating blendshapes for models with multiple disconnected parts. We present a case study of generating fixed facial expression blendshapes for commercial anime-style 3D character models with up to 11 parts per face. To make sure that our system can handle models in a way that is agnostic to topology, we train neural networks to generate...
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.