Stars
Download scripts for EPIC-KITCHENS
CineCLI is a cross-platform command-line movie browser built with Python.
这是一个YoloV4-tiny-pytorch的源码，可以用于训练自己的模型。
YOLOv4, YOLOv4-tiny, YOLOv3, YOLOv3-tiny Implemented in Tensorflow 2.0, Android. Convert YOLO v4 .weights tensorflow, tensorrt and tflite
RLinf is a flexible and scalable open-source infrastructure designed for post-training foundation models (LLMs, VLMs, VLAs) via reinforcement learning.
The absolute trainer to light up AI agents.
A unified library for object tracking featuring clean room re-implementations of leading multi-object tracking algorithms
[ICCV 2025] Gaussian Variation Field Diffusion for High-fidelity Video-to-4D Synthesis
Official repo for paper "Structured 3D Latents for Scalable and Versatile 3D Generation" (CVPR'25 Spotlight).
Point-Voxel Interaction LiDAR Scene Upsampling Via Diffusion Models
Code for "PVNet: Pixel-wise Voting Network for 6DoF Pose Estimation" CVPR 2019 oral
👨💻 Python cleanup script for macOS
[CVPR2021] Real-Time Sphere Sweeping Stereo from Multiview Fisheye Images
Official Implementation of "Dens3R: A Foundation Model for 3D Geometry Prediction"
DeepCalib: A Deep Learning Approach for Automatic Intrinsic Calibration of Wide Field-of-View Cameras
[NeurIPS 2024] Depth Anything V2. A More Capable Foundation Model for Monocular Depth Estimation
Open standard for machine learning interoperability
[CVPR 2022 Best Student Paper] EPro-PnP: Generalized End-to-End Probabilistic Perspective-n-Points for Monocular Object Pose Estimation
AI-augmented development in Vim and Neovim
Code release for CVPR'24 submission 'OmniGlue'
SuperGlue: Learning Feature Matching with Graph Neural Networks (CVPR 2020, Oral)
Code for "Efficient LoFTR: Semi-Dense Local Feature Matching with Sparse-Like Speed", CVPR 2024
Agent Reinforcement Trainer: train multi-step agents for real-world tasks using GRPO. Give your agents on-the-job training. Reinforcement learning for Qwen2.5, Qwen3, Llama, and more!
RynnEC: Bringing MLLMs into Embodied World