AI & Machine Learning · Computer Science & AI
Computer Vision
The newest papers in Computer Vision that ReadSearch has read, newest first. Each links to its own page, with its authors, date, where it was published and the original.
The newest 5,000 papers, from 29 September 2026 to 5 November 2026: 4,996 arXiv preprints and 4 OpenAlex records.
Get the few papers worth your time in Computer Vision every morning.
Follow Computer Vision and ReadSearch reads its new papers each day, then brings you the few worth reading, each with its key finding in a sentence.
Newest papers, page 213
Custom Forcing: Training-Free Subject Customization for Autoregressive Video Generation
Autoregressive video models can generate minute-long videos in real time, but they produce generic subjects from text rather than specific subjects from user-provided images.Kinematics-Induced Multimodal 3D Human Pose Estimation with Subject-Level Privacy
Multimodal 3D Human Pose Estimation (3D HPE) combines complementary information from RGB, LiDAR, and mmWave radar, but models trained on correlated observations from the same individuals, raise…When Predicting Nothing Beats SAM 3: Revisiting Evaluation in Video Object Segmentation
Video Object Segmentation (VOS) in complex and long videos is increasingly important for real-world applications, where target objects often appear only intermittently within long temporal horizons.TerraVis: Towards Evaluation of World-Grounded Visual Consistency in Text-to-Image Generation via MLLM Workflows
Recent text-to-image models have made substantial progress in photorealism, aesthetics, and text-image alignment.Post-Training Frontier Text-to-Image Models by Composing Preference and Rubric Rewards
Recent text-to-image generation models have achieved remarkable visual quality, but improving them through post-training remains challenging because no single reward signal captures the full range…From Language Priors to Field Adaptation: Preference Learning for Traversability Estimation
Image-based traversability estimation is inherently dependent on the robot platform, deployment domain, and mission preferences, which limits the applicability of purpose-trained models.Recursive Self-Improvement in Unified Multimodal Models
Unified multimodal models (UMMs) understand and generate both text and images, which lets a model produce its own training data.Rethinking Fixed Temporal Grids: Frequency-Disentangled Motion Generation
Most human motion generation methods encode motion as tokens on a uniform temporal grid, where every token spans the same fixed time window.RYOPO: Bringing End-to-End Category-Level Object Pose Estimation into Real Time
Category-level object pose estimation predicts the rotation, translation, and metric size of unseen instances within known categories.OmniAct3D: Leveraging Foundation Geometry and Evidence-Grounded Reasoning for Panoramic 3D Detection
Accurate 3D detection is essential for mobile embodied agents, while Vision Foundation Models (VFMs) offer transferable visual and geometric priors.From Expression to Reaction: Role-aware Visual Transfer and Stimulus-guided Reasoning for Interlocutor Emotion Recognition
In this paper, we propose a Role-aware Stimulus-guided (RASG) framework for interlocutor emotion recognition, which predicts listener emotions from listener-only videos and speaker-only audios.ReSCUE: Re-translation with Sentence Commitment for Unsegmented Long-Form Simultaneous Sign Language Translation
Simultaneous Sign Language Translation (SLT) is critical for real-time communication, yet existing methods remain largely confined to sentence-level, offline settings that assume pre-segmented inputs.CrowdOcc: Monocular Semantic Scene Completion for Quadruped Robots in Crowded Indoor Environments
Monocular semantic scene completion (SSC) for quadruped robots remains underexplored in real crowded indoor environments, where human-scene occlusion disrupts static geometry and human occupancy…Adaptive Second-Order Solvers for Fast Stochastic Diffusion Sampling
Diffusion models rely on numerical solvers requiring time-discretization, which has a large influence on the tradeoff between sampling cost and quality.WebFovea: When the Model Is Right but the Click Is Wrong -- Reliable Round Trips for Vision-Based Web Agents on Live Websites
We present WebFovea, a vision-based web agent that placed 2nd in the WebRetriever Challenge 2026 with a final score of 57.0 out of 100.Parasitic Co-Denoising: Unlocking 3D Human Motion Generation in a Frozen Video Diffusion Model
Despite never being supervised on explicit 3D motion, large-scale text-to-video diffusion models synthesize realistic human motion in their generated videos.BeeWhere: Segmenting Bumble Bee Colonies to Quantify Behavioral Effects
Social bees are important pollinators that support biodiversity and crop pollination globally and serve as important model systems for collective behavior, but scalable measurement of individual-…Where to Look Is Not How to Fix: Pre-Denoising Diagnostics and Modality-Dependent Control in Diffusion Composition
Understanding compositional failures in text-to-image diffusion requires identifying both where stress is detectable and how intervention changes the output.NegT2IBench: When Negation Changes the Picture. A Polarity Benchmark for Text-to-Image Models
Text-to-image (T2I) models are judged by benchmarks that measure whether requested content appears, but these benchmarks largely overlook the complementary ability to satisfy negated constraints…Beyond Single Videos: Benchmarking and Active Evidence Seeking for E-Commerce Cross-Video Reasoning
E-commerce videos are information-dense and frequently compared by consumers evaluating products and merchants assessing marketing strategies.