Latest Research in Computer Vision and Pattern Recognition
40 research papers · 2026 median publication year
Top Research Topics in Computer Vision and Pattern Recognition
- Computer Vision and Pattern Recognition — 26 papers
- Advanced Vision and Imaging — 6 papers
- Image and Video Processing — 2 papers
- Robotics and Sensor-Based Localization — 2 papers
- Underwater Vehicles and Communication Systems — 1 papers
- Robotics — 1 papers
- Optics — 1 papers
- Zebrafish Biomedical Research Applications — 1 papers
Highest-Cited Papers
- Autonomous docking experiments for underwater spherical robot based on visual guidance with improved detection transformer
- PolyLayout: Multi-room Manhattan Layout Estimation
- Efficient Monocular Depth Estimation on Embedded Systems with Neural Cellular Automata
- Gaussian Belief Propagation Network for Depth Completion
- RIDE: Relocalization-Informed Depth Estimation with 3D Gaussian Splatting
- Reducing Depth Measurement Uncertainty in Industrial Robot Stereo Vision Through Error-Aware Disparity Refinement
- Marigold V2: Revisiting Diffusion Transformers for Monocular Depth Estimation
- GALoc: Gravity Aligned Wireframes for Depth-Free Monocular Floorplan Localization
- OmniPoint: Universal Monocular Metric Pointcloud from Any Camera
- Online dynamic scene reconstruction based on multi-view video
- UniFusion: Sparse-View 4D Reconstruction via Unified Spatio-temporal Depth Alignment
- Towards Robust Driving Perception: A Flexible Scale-Driven Family for Self-Supervised Monocular Depth Estimation
- AI-based single-shot structured-light depth reconstruction for real-time laparoscopic surgical guidance
- CrossDepth: Geometry-Constrained Attention for Generalizable Multi-View Surround Depth Estimation
- Weather-Conditioned Depth Anything
- Pixel-wise Planarity for High-Precision Monocular Plane Segmentation
- Vision3D: A Full-Stack Framework for Monocular Single-Image 3D Scene Reconstruction with Depth– Object Semantic Fusion
- Vision3D: A Full-Stack Framework for Monocular Single-Image 3D Scene Reconstruction with Depth– Object Semantic Fusion
- When Depth Hurts: Reliability-Aware Geometry Distillation for Depth-Free RGB-D Salient Object Detection
- Zero-Shot Novel Depth Synthesis Using 3D Foundation Models Scene Representations