[TCSVT] CorrI2P: Deep Image-to-Point Cloud Registration via Dense CorrespondenceThe code of CorrI2P

[CVPR 2026] UniCorrn: Unified Correspondence Transformer Across 2D and 3D

DeepSeek-V4-Flash on Ampere SM 8.6 via vLLM (pyref kernel replacements)

[CVPR 2026 Findings] Speed3R: Sparse Feed-forward 3D Reconstruction Models

[CVPR 2025] Fast3R: Towards 3D Reconstruction of 1000+ Images in One Forward Pass

HY-World 2.0: A Multi-Modal World Model for Reconstructing, Generating, and Simulating 3D Worlds

从零搭建 AI 猫猫协作系统 — 一个真实项目的完整复盘

Build AI teams, not just agents. Hard rails, soft power, shared mission.

An open-source Collaborative Multi-Agent OS for transparent, human-in-the-loop task coordination via Matrix rooms.

An agentic skills framework & software development methodology that works.

The open source coding agent.

Your own personal AI assistant. Any OS. Any Platform. The lobster way. 🦞

An open-source AI coding agent that lives in your terminal.

[CVPR2025] From Sparse to Dense: Camera Relocalization with Scene-Specific Detector from Feature Gaussian Splatting

Code for "LiftFeat: 3D Geometry-Aware Local Feature Matching", ICRA2025

News: the 10k dataset is ready for download.

[ICML 2026] WorldMirror: Fast and Universal 3D reconstruction model for versatile tasks

Cameras as Relative Positional Encoding

3DGS-to-PC: 3D Gaussian Splatting to Dense Point Clouds [3D-VAST: ICCVW 2025]

Dataset and Code for CVSports at CVPR 2025 paper "AthletePose3D: A Benchmark Dataset for 3D Human Pose Estimation and Kinematic Validation in Athletic Movements"

[CVPR'25] CoMatcher: Multi-View Collaborative Feature Matching

"AI-Trader: 100% Fully-Automated Agent-Native Trading"

[NeurIPS 2025] Pixel-Perfect Depth

[ICCV2025 Highlight]: SGAD: Semantic and Geometric-aware Descriptor for Local Feature Matching

Anthropic's Interactive Prompt Engineering Tutorial

Reference PyTorch implementation and models for DINOv3

Visual localization made easy with hloc

MapAnything: Universal Feed-Forward Metric 3D Reconstruction