Latest Research in Computer Vision and Pattern Recognition
30 research papers · 2026 median publication year
Top Research Topics in Computer Vision and Pattern Recognition
- Computer Vision and Pattern Recognition — 23 papers
- 3D Shape Modeling and Analysis — 3 papers
- Computer Graphics and Visualization Techniques — 1 papers
- Robot Manipulation and Learning — 1 papers
- Robotics and Sensor-Based Localization — 1 papers
- Human-Computer Interaction — 1 papers
Highest-Cited Papers
- Generative Integration of CG Decomposition and Dual Structures for Stable Geometric Flows
- G2G: Exploiting Intra-Group Geometry for Inter-Group Pose Estimation
- Frame-wise 3DGS-based Human Point Cloud Generation With Gaussian Primitive-aware Upsampling From Fixed Multiview GoPro Videos
- What Makes a 3D Scene Editable? A Factorized Benchmark of Fidelity, Locality, Consistency, and Preservation
- Recursive Code World Models: Building Complex Worlds through Recursive Scene Programs
- SkyAnchor: Updating Metric-scale Aerial 3D Gaussian Scenes from Unposed Ground-View Sequences
- RIGOR: Rig-Informed Geometry for Omnidirectional Reconstruction
- Image-based visual servoing and graph matching: a strategy for high-precision robotic assembly
- A Calibration Audit of Confidence in Feed-Forward 3D Reconstruction Models
- Learn the Solid, Not the File: Canonical Inputs for Neural Networks on CAD Boundary Representations
- Learning Global Camera Poses from Noisy View-Graphs for Structure from Motion
- 3DHarnessBench: Probing Agentic 3D-to-Code Capabilities of Frontier Vision-Language Models
- Back to the Feature: Zero-Shot 6DoF Pose Estimation via Dense Local Features
- Sparse auto-regressive modeling for scene generation from multi-view images
- Scal3R: Learning Efficient Multi-Relative Pose Query for Scalable Online 3D Reconstruction
- Rethinking 3D Noise: Learning 3D-Aware Video Priors via Optimization-Free Morphological Perturbations
- DIAL-GS: Dynamic Instance Aware Reconstruction for Label-free Street Scenes with 4D Gaussian Splatting
- OpenAsset: A Pipeline for Open-World Asset Integration into Indoor Scene Synthesis
- Geometry-Guided Modeling of Foundation Features Enables Generalizable Object Shape Deformation Learning
- Contact-graph-guided digital twin construction and incremental update for discrete manufacturing cells