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 196
RACER: Reflective Agent Coupling Query Interpretation and Tool-Based Retrieval for Frame Selection in Long Video Understanding
Video large language models (Vid-LLMs) excel at diverse video-language tasks by reasoning over selected frames.S2Tok: Streaming 3D Gaussian Reconstruction with Persistent Spatial Tokens
Streaming 3D reconstruction requires more than a sequence of geometric predictions: it requires a persistent scene state that can incorporate new evidence and remain renderable as observations arrive.Zero-Shot Brain MRI Inpainting with 2.5D Unconditional Flow Priors
Generative inpainting of brain MRI volumes is essential for synthesizing healthy tissue in pathological regions, improving the accuracy and reliability of automated downstream brain analysis…Personalize at Test Time: Learning User Preferences for Image Generation
Diffusion models can generate high-quality images, yet aligning their outputs with individual user preferences remains challenging.Visual Memory Attacks Can Persist Through The KV Cache
Modern language model systems operate autonomously over increasingly long contexts containing untrusted text and images.Beyond Explanation: Debugging Medical Imaging Models via Concept Intervention
Medical imaging models often operate as black boxes, limiting interpretability and systematic debugging.Shape-Bayes: Bayesian Inference of Structured Shapes under Visual Ambiguity
Perceiving structured shapes, such as human faces, from pixels is an inherently ambiguous task in real-world conditions.GUARD: Geometric Uncertainty-Aware Point Cloud Denoising and Segmentation for Robotic Hard Disk Drive Disassembly
Reliable robotic disassembly requires part-level representations that distinguish genuine component geometry from scanning and reconstruction artifacts.OverLay++: Dense-Overlap Layout-to-Image Generation Dataset
Layout-to-Image generation has made substantial progress in spatial and object-level control.DISRQAD: Diffusion Image Super-Resolution Quality Assessment Dataset and Benchmark
Diffusion-based image super-resolution (SR) can create visually plausible detail that is not supported by the low-resolution input.Large-scale Repository Engineering via Agent-Native Reusable Code Primitives
Large language models equipped with development environments have moved code generation toward repository-scale construction, yet building complete repositories remains difficult because interacting…Anaximander: Interactively Running Geospatial Deep Learning Models on Any Compute Backend
Applying deep learning models to satellite imagery from within geographic information systems (GIS) remains high-friction for remote sensing practitioners.SPLATIFY: Reproduce, Discover, Innovate! From Papers and Ideas to Trainable 3DGS Code
The rapid growth of 3D Gaussian Splatting (3DGS) research demands significant effort to reimplement papers before building on them.TopoCurve: Geometry-Aware Topology Reasoning via Bézier Curves in Autonomous Driving
Topology reasoning jointly detects 3D lanes and traffic elements from multi-view images and infers their structural connectivity.Depth-to-RGB: Repurposing a Frozen Depth Estimator for Geometry-Guided Compositing
Reference-based object compositing inserts or replaces an object using a background image, a reference image, and a 2D compositing mask.RDGSplat: Render-Dedicated Geometry for Novel View Synthesis
3D foundation models enable efficient novel view synthesis by carrying a Gaussian head on the representation they already use for reconstruction.One Frame, Full Heartbeat: ECG-Free 4D Cardiac Cine MRI Synthesis via Radial-Decomposed Flow Matching
Cine cardiovascular magnetic resonance (CMR) captures the cardiac cycle as a four-dimensional (4D) sequence, but standard acquisition requires electrocardiogram (ECG) gating and repeated breath holds.R-CNN-Based Chess Position Recognition
Performing chess game position recognition solely from a single image of a three-dimensional board requires predicting the position and orientation of the board relative to the camera, the occupancy…StableGrasp: Reconstructing Physically Stable Human Hand Grasps from Single Images
Reconstructing a physically stable human grasp from a single RGB image is challenging because physically modeling grasps is itself difficult, and the problem requires estimating not only a visually…StyleFields: Multi-Scale AdaIN-Modulated Implicit SDFs for Coarse-to-Fine 3D Shape Reconstruction and Editing
We introduce StyleFields, a DeepSDF-based architecture for high-fidelity 3D reconstruction that enables controllable geometric style mixing: the coarse structure of one object can be combined with…