-
Wuhan University
- Wuhan China
- https://space.bilibili.com/472061452
- https://orcid.org/0000-0002-5283-9057
Highlights
- Pro
Lists (12)
Sort Name ascending (A-Z)
Starred repositories
⚡ A Fast, Extensible Progress Bar for Python and CLI
FAIR's research platform for object detection research, implementing popular algorithms like Mask R-CNN and RetinaNet.
Mask R-CNN for object detection and instance segmentation on Keras and TensorFlow
Original reference implementation of "3D Gaussian Splatting for Real-Time Radiance Field Rendering"
pix2tex: Using a ViT to convert images of equations into LaTeX code.
End-to-End Object Detection with Transformers
[CVPR 2025 Best Paper Award] VGGT: Visual Geometry Grounded Transformer
A collaboration friendly studio for NeRFs
Robust Video Matting in PyTorch, TensorFlow, TensorFlow.js, ONNX, CoreML!
Faster R-CNN (Python implementation) -- see https://github.com/ShaoqingRen/faster_rcnn for the official MATLAB version
CUDA accelerated rasterization of gaussian splatting
LightGlue: Local Feature Matching at Light Speed (ICCV 2023)
Deformable DETR: Deformable Transformers for End-to-End Object Detection.
Open source Structure-from-Motion pipeline
A genetic algorithm toy project for drawing
[CVPR'24 Highlight & Best Demo Award] Gaussian Splatting SLAM
[ECCV 2024] Street Gaussians: Modeling Dynamic Urban Scenes with Gaussian Splatting
Python tools for working with KITTI data.
A 3DGS framework for omni urban scene reconstruction and simulation.
这是一本关于SLAM的书稿,希望能清楚的介绍SLAM系统中的使用的几何方法和深度学习方法。书稿最后应该会达到200页左右,书稿每章对应的代码也会被整理出来。
Fisheye or Normal Camera Intrinsic and Extrinsic Calibration. Surround Camera Bird Eye View Generator.
Convert KITTI dataset to ROS bag file the easy way!
UrbanLoco: A Full Sensor Suite Dataset for Mapping and Localization in Urban Scenes
Code for the paper "High Speed and High Dynamic Range Video with an Event Camera" (T-PAMI, 2019).
converts image sequence in ros bag files to video files
Code for the paper "Low Latency Automotive Vision with Event Cameras", published in Nature
Integrating Feed-Forward Visual Model with IMU, GNSS for High-Functionality SLAM.