-
The Chinese University of Hong Kong
- Hong Kong
- https://fishmarch.github.io
Stars
[ECCV 2024] This is the official implementation of HRMapNet, maintaining and utilizing a low-cost global rasterized map to enhance online vectorized map perception.
[JFR 2024] This is the official implementation of MS-SLAM, a memory-efficient visual SLAM system removing redundant map points to save memory consumption.
MTR: Motion Transformer with Global Intention Localization and Local Movement Refinement, NeurIPS 2022.
[ICCV 2023 Oral] Game-theoretic modeling and learning of Transformer-based interactive prediction and planning
A community maintained fork of the inactive ORB_SLAM3 project
This is the official implementation of the work presented at CVPR 2024, titled Multiple View Geometry Transformers for 3D Human Pose Estimation (MVGFormer).
Implemented BEVFormer support for BEV segmentation
Vision-based 3D occupancy prediction in autonomous driving: a review and outlook
[CVPR24] COTR: Compact Occupancy TRansformer for Vision-based 3D Occupancy Prediction
[ECCV 2024] This is the official implementation of MapQR, an end-to-end method with an emphasis on enhancing query capabilities for constructing online vectorized maps.
[CVPR 2024] Neural Markov Random Field for Stereo Matching
arXiv LaTeX Cleaner: Easily clean the LaTeX code of your paper to submit to arXiv
[ICCV 2023] Predict to Detect: Prediction-guided 3D Object Detection using Sequential Images
A library for differentiable nonlinear optimization
Modular, open-source implementations of continuous-time simultaneous localization and mapping algorithms.
Blender add-on for creating OpenDRIVE and OpenSCENARIO based automotive driving scenarios including 3D models
SLAM-Map-Compression-OR-Tools
[ICLR'23 Spotlight & IJCV'24] MapTR: Structured Modeling and Learning for Online Vectorized HD Map Construction
fishmarch / ORB_SLAM3_Fixed
Forked from UZ-SLAMLab/ORB_SLAM3Fixed some bugs of original ORB_SLAM3
Remove bad map points and keyframes to save memory.
[CVPR 2023] Efficient Map Sparsification Based on 2D and 3D Discretized Grids
《动手学深度学习》:面向中文读者、能运行、可讨论。中英文版被70多个国家的500多所大学用于教学。
The repository includes evidence that a published paper in TKDE shares surprisingly high similarity to our paper.
📷 📷 Stereo camera calibration using OpenCV and C++
Python package for the evaluation of odometry and SLAM
My assignments for Stanford CS231n in Spring 2021