[DEIMv2] Real Time Object Detection Meets DINOv3

[CVPR 2025] SAT-HMR: Real-Time Multi-Person 3D Mesh Estimation via Scale-Adaptive Tokens

The official CPLP implementation from Prioritised Planning for Continuous-time Lifelong Multi-agent Pathfinding.

DAA*: Deep Angular A Star for Image-based Path Planning, ICCV 2025

Camera calibration with sub-pixel accuracy: https://discorpy.readthedocs.io/

RepViT: Revisiting Mobile CNN From ViT Perspective [CVPR 2024] and RepViT-SAM: Towards Real-Time Segmenting Anything

[CVPR25] Official implementation of `MobileMamba: Lightweight Multi-Receptive Visual Mamba Network.'

OmniGen2: Exploration to Advanced Multimodal Generation.

Implementation of ORCA algorithm

lib release of paper [TopoTag: A Robust and Scalable Topological Fiducial Marker System]

Official implementation of paper [DeepTag: A General Framework for Fiducial Marker Design and Detection]

Kinodynamic-CBS (K-CBS) is a decentralized motion planning algorithm capable of solving complex multi-agent motion planning queries for agent with complex, possibly unique, kinodynamic constraints.

JAX-based implementation for multi-agent path planning (MAPP) in continuous spaces.

PillarNeXt: Rethinking Network Designs for 3D Object Detection in LiDAR Point Clouds (CVPR 2023)

[CVPR 2025] JamMa is a lightweight image matcher that enables fast internal and mutual interaction of images with joint Mamba.

[NeurIPS24 Spotlight] Voxel Mamba: Group-Free State Space Models for Point Cloud based 3D Object Detection

[CVPR2025] Implementation of "FSHNet: Fully Sparse Hybrid Network for 3D Object Detection"

SIMD-Accelerated Sampling-based Motion Planning

GPU-Parallel RRT-Connect

This repository contains the implementation (RT-FMT) algorithm, as proposed in the paper titled "Real-Time Fast Marching Tree (RT-FMT) for Mobile Robot Motion Planning in Dynamic Environments"

Python parser for URDFs

A Modular Toolkit for Robot Kinematic Optimization

Kimi-Audio, an open-source audio foundation model excelling in audio understanding, generation, and conversation

[CVPR 2023] Official implementation of the paper "Mask DINO: Towards A Unified Transformer-based Framework for Object Detection and Segmentation"

[CVPR'25 Highlight] Official repository of Sonata: Self-Supervised Learning of Reliable Point Representations

[CVPR'24 Oral] Official repository of Point Transformer V3 (PTv3)