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: 4,999 arXiv preprints and 1 OpenAlex record.
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 4
Learning Robotic World Models with Semantic and Visual Feedback
Robot world models predict action-conditioned future visual states to support robotic planning and decision making.OcTreeMamba: Topology-Aware Mamba for 3D Medical Segmentation via Octree Sparsification
Accurate segmentation of 3D anatomical structures is crucial to medical image analysis.PlayGen2: Learning Real-Time Playable Worlds with Explicit 3D State
Building a playable world requires more than generating plausible video: it demands responsive control, persistent spatial structure, and coherent interactions with dynamic entities.PVDepth: Panoramic Video Depth Estimation via Geometry-Aware Spatiotemporal Adaptation
Panoramic video depth estimation is pivotal for applications such as Virtual Reality and World Models.InnerLogic-Surg: An Open Surgical Foundation Model via Continual Pretraining
Vision foundation models are the backbone of modern surgical image analysis, yet most surgical systems still rely on encoders pretrained on natural images or on specialist models trained from…Structure from Collision via Hypothesis-Space Reasoning
Knowledge of the hidden interior structure of an object, including the presence and location of cavities, is essential for predictive simulation, robotic manipulation, and nondestructive inspection.XM4D: 4D Reconstruction through Certifiable Geometric Optimization
Accurate 4D reconstruction remains challenging: jointly estimating camera motion, scene geometry, and non-rigid deformation entails highly nonconvex optimization, making global optimality difficult…EDGAR: Efficient Diffusion-Driven Gaussian Avatar Refinement via Synthetic Failure
Recent advances in Gaussian splatting have enabled efficient and photorealistic head avatar reconstruction, yet monocular video-based or image-based methods still suffer from under-constrained…StitchEdit: Stitching Depth Priors into Image Editors via Per-Layer Gradient Probing
Text-guided image editing with diffusion models struggles with spatial edits (e.g. manipulating objects, changing viewpoints, manipulating occlusions) that depend on the 3D structure understanding…Flux as a Codec: Zero-Shot Lossy Compression with Flux
We propose FluxC, a zero-shot codec that uses Flux as a compression prior.Towards Scalable Diagnostic-Driven Whole-Slide Image Retrieval for Pathology Archives
The growing adoption of digital pathology has rapidly expanded collections of hematoxylin-and-eosin whole-slide images, yet efficient navigation through these archives remains challenging, as…WAM-Sim0.1: World Anchored Memory Meets Online RL for Consistent and Realistic Driving Simulation
Autoregressive driving world models systematically suffer from structural drift, identity drift, and quality decay over long rollout horizons due to transient conditioning signals that lack…IDPrior: Decoupling Identity Generation from Facial Image Synthesis
Large-scale identity-labeled face datasets are essential for training modern face recognition models, yet collecting and annotating such data is costly and raises privacy and ethical concerns.Leakage- and Label-Aware Benchmarking of Class-Imbalance Strategies for Multimodal Chest X-Ray and EHR Classification
Benchmarks of class-imbalance strategies for multimodal chest X-ray (CXR) and electronic health record (EHR) prediction are often evaluated on record-level splits of cohorts in which one patient…Rotation Is Token-Blind: A Structural Criterion for Post-Training Quantization of Feed-Forward Geometry Transformers
Feed-forward 3D models use Transformers to predict camera poses, depth, and structure in one pass, avoiding iterative multi-view optimization.Bri3D: Bridging the Object-Scene Gap in Single-Image 3D Generation via Scene-Anchor
Generating compositional 3D scenes from a single image requires recovering detailed object geometry and coherent spatial arrangements.Reviving the Discarded High-Resolution Feature for Transformer-Based Tiny Object Detection
Tiny object detection remains challenging because tiny instances occupy only a few pixels, and their fine-grained details are easily lost during feature downsampling.When GeoFMs Meet VHR: Benchmarking Foundation Models on Very High Resolution Earth Observation Imagery
Geospatial foundation models are a widely adopted starting point for remote sensing tasks.Deformable Contact-Aware 3D Object Placement
Current language-guided 3D object placement typically predicts a rigid 6-DoF pose, ignoring the physical reality that indoor placements are dictated by contact.NutriVisRAG: Multimodal Exemplar Grounding for Nutrient Estimation with Vision-Language Models
Diet is a major determinant of health, yet accurate dietary assessment from free-living meal images remains challenging.