🤗 LeRobot: Making AI for Robotics more accessible with end-to-end learning

[SIGGRAPH ASIA 2025] This is the official implementation of the SIGGRAPH ASIA 2025 : Hierarchical Neural Semantic Representation for 3D Semantic Correspondence

[RSS 2023] Diffusion Policy Visuomotor Policy Learning via Action Diffusion

[CVPR 2025 Best Paper Award] VGGT: Visual Geometry Grounded Transformer

SIGGRAPH 2025

COLMAP - Structure-from-Motion and Multi-View Stereo

This is the official repo for paper "StableMotion: Repurposing Diffusion-Based Image Priors for Motion Estimation"

Implementation of π₀, the robotic foundation model architecture proposed by Physical Intelligence

[Lumina Embodied AI] 具身智能技术指南 Embodied-AI-Guide

[AAAI 2025 Oral] FlowPolicy: Enabling Fast and Robust 3D Flow-based Policy via Consistency Flow Matching for Robot Manipulation

[AAAI 2025] HybridReg: Robust 3D Point Cloud Registration with Hybrid Motions, PyTorch implementation.

DeepSeek-VL2: Mixture-of-Experts Vision-Language Models for Advanced Multimodal Understanding

Official repo for paper "Structured 3D Latents for Scalable and Versatile 3D Generation" (CVPR'25 Spotlight).

🤗 image matching webui

Blue noise for diffusion models [SIGGRAPH 2024]

A generative world for general-purpose robotics & embodied AI learning.

[ECCV 2024] PointRegGPT: Boosting 3D Point Cloud Registration using Generative Point-Cloud Pairs for Training, Pytorch implementation.

[AAAI 2025] HybridReg: Robust 3D Point Cloud Registration with Hybrid Motions, PyTorch implementation.

QRec is an algorithm that helps you quickly find the largest fixed-aspect, axis-aligned rectangle that can be inscribed in any given polygon.

This is the official implementation of YOLA, NeurIPS2024

[SIGGRAPH 2024] Motion I2V: Consistent and Controllable Image-to-Video Generation with Explicit Motion Modeling

This repository contains the code for our CVPR2024 paper "Harnessing Meta-Learning for Improving Full-Frame Video Stabilization".

本人的科研经验