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 227
A Simulation-Grounded Agentic VLM Framework for Wildfire Monitoring and Reporting
Effective wildfire monitoring requires relating visual evidence to physical fire dynamics, yet real videos with synchronized physical annotations are scarce and high-fidelity 3D simulation is costly.Windfoil: Closed-Form Coverage for Real-Time and Differentiable Vector Graphics
We present Windfoil, a GPU-friendly algorithm that treats rasterisation and differentiable vector graphics as two sides of the same problem by evaluating the box-filtered winding number of quadratic…DeepStratNet: A Context-Aware Coordinate Regression Framework for Seismic Horizon Tracking under Sparse Labels
Automatic horizon tracking is a foundational task in 3D seismic interpretation.MeshQuery: Agentic Seam Planning for UV Parametrization
We present MeshQuery, a training-free agentic approach to automatic UV unwrapping of production-grade quad meshes.World Action Modeling with Progressive Visual Planning
World action models (WAMs) have emerged as a promising paradigm for robotic control by jointly predicting future visual dynamics and actions from an initial observation and instruction.From Fragments to Global Maps: Learning Vectorized Map Aggregation with Large Language Models
Large-scale vectorized HD maps provide structured road information that is essential for perception, localization, and planning in autonomous driving.Spatial Memory Intelligence: Endowing World Models with Understanding-Driven Long-Term Memory
Long-video generation and world models have shown strong potential for interactive entertainment and embodied simulation by predicting future observations conditioned on user actions and historical…Oracle headroom without signal: null-calibrated evaluation of candidate selection for thermal heart rate estimation
Camera-based physiological monitoring can produce multiple estimates from several facial regions, extraction methods, and processing settings.DAGS: Disentangled Appearance-and-Geometry Steering of a Frozen Image DiT for Temporally Stabilized Generative Rendering
Diffusion transformers (DiTs) generate high-fidelity images from text and image conditions, but their outputs carry large variance and their faithfulness to a desired target depends heavily on how…Physical AI Smart Spaces: A Large-Scale Benchmark for Multi-Camera 3D Perception in Smart Spaces
Physical AI Smart Spaces is, to the best of our knowledge, the first benchmark to simultaneously provide large-scale, multi-class, and multi-camera 3D perception data for indoor smart spaces.GRAFT: Growing Agglomerative Foundation Models via Continual Teacher Distillation
Vision foundation models such as DINOv2, SigLIP2, and MASt3R develop complementary capabilities from different pretraining objectives, yet their knowledge remains distributed across separate…WAMJET: A Harness for World Action Model Acceleration
World Action Models (WAMs) leverage pretrained video foundation models for robot manipulation, but their large backbones and video-action co-prediction are expensive.StepCAD: Mesh-to-CAD Code Generation via LLM Policy and Geometry-Guided Search
Recovering executable CAD programs from 3D meshes is challenging due to the compositional nature of CAD construction and the interaction between discrete modeling choices and continuous parameters.Least Squares for Time Series Forecasting
A time-series forecast is scored on a future value of the series.Image-Based Breast Implant Detection for Mammography Dataset Curation and Near-Real-Time Deployment: Comparing Foundation Models and Task-Specific Convolutional Models
To evaluate the performance-feasibility tradeoffs of foundation models (FMs) and task-specific convolutional neural networks (CNNs) trained from scratch for breast implant classification in 2D…GEODE: Symmetry-Preserving Cartesian Diffusion for Crystal Generation
Most known inorganic crystals exhibit symmetric atomic arrangements, yet generative models often fail to reproduce them.ReGain: Restoring Subject Fidelity in Personalization on Synthetic Images
Text-to-image diffusion models are personalized to a subject by DreamBooth fine-tuning on a handful of its images.Unveiling the Value of Motion for Cinematic Camera Trajectories
Cinematic camera motion is a fundamental storytelling tool, defined not only by where the camera is positioned in the scene, but also by how it moves in terms of direction and speed.EPIC: Epipolar-Consistent 360° Immersive Stereo Video Generation
Immersive displays can enable rich and diverse virtual experiences.No Corners Cut: State-Grounded Transitions for Mid-Stream Prompt Switches in Video Generation
Streaming video generators allow users to dynamically modulate video synthesis via mid-stream prompt switching.