Hailanyi

DetAny3D. A demo page for DetAny3D

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

WeatherDG. [RA-L] Generate Weather with LLM. Code for "WeatherDG: LLM-assisted Procedural Weather Generation for Domain-Generalized Semantic Segmentation"

Colosseum. Open source simulator for autonomous robotics built on Unreal Engine with support for Unity

carla. Open-source simulator for autonomous driving research.

MMAUD. [ICRA-2024] MMAUD: A comprehensive multi-modal anti-UAV dataset for modern miniature drone threats

MAV6D.

DeepSeek-V3. Python

V2X-R. CVPR 2025 - V2X-R: Cooperative LiDAR-4D Radar Fusion for 3D Object Detection with Denoising Diffusion

MCTrack. [IROS2025]This is the offical implementation of the paper "MCTrack: A Unified 3D Multi-Object Tracking Framework for Autonomous Driving"

CMD. Data and code for ECCV2024 paper "CMD: A Cross Mechanism Domain Adaptation Dataset for 3D Object Detection".

CPD. Commonsense Prototype for Outdoor Unsupervised 3D Object Detection (CVPR 2024)

SUSTechPOINTS. 3D Point Cloud Annotation Platform for Autonomous Driving

DRIFT. Python

PSA-Fusion. Python

GPT4Point. [CVPR'24 Highlight] GPT4Point: A Unified Framework for Point-Language Understanding and Generation.

pykan. Kolmogorov Arnold Networks

grok-1. Grok open release

gim. GIM: Learning Generalizable Image Matcher From Internet Videos (ICLR 2024 Spotlight)

Occupancy-MAE. Official implementation of our TIV'23 paper: Occupancy-MAE: Self-supervised Pre-training Large-scale LiDAR Point Clouds with Masked Occupancy Autoencoders

TED. Transformation-Equivariant 3D Object Detection for Autonomous Driving

lidar_simulation. Simulate lidar measurements on .obj 3D-models

MODEST. Code release for "Learning to Detect Mobile Objects from LiDAR Scans Without Labels" [CVPR 2022]

lift-splat-shoot. Lift, Splat, Shoot: Encoding Images from Arbitrary Camera Rigs by Implicitly Unprojecting to 3D (ECCV 2020)

MiniGPT-4. Open-sourced codes for MiniGPT-4 and MiniGPT-v2 (https://minigpt-4.github.io, https://minigpt-v2.github.io/)

BLIP. PyTorch code for BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation

unimatch. [TPAMI'23] Unifying Flow, Stereo and Depth Estimation

occupancy_networks. This repository contains the code for the paper "Occupancy Networks - Learning 3D Reconstruction in Function Space"

CompletionFormer. [CVPR2023] CompletionFormer: Depth Completion with Convolutions and Vision Transformers

LiDAR_ground_removal. This is an implement of Fast Segmentation of 3D Point Clouds for Ground Vehicles

efinance. efinance 是一个可以快速获取基金、股票、债券、期货数据的 Python 库，回测以及量化交易的好帮手！🚀🚀🚀

SLOPER4D. SLOPER4D: A Scene-Aware Dataset for Global 4D Human Pose Estimation in Urban Environments (CVPR2023)

GD-MAE. GD-MAE: Generative Decoder for MAE Pre-training on LiDAR Point Clouds (CVPR 2023)

VirConv. Virtual Sparse Convolution for Multimodal 3D Object Detection

UG3DMOT. Python

apollo. An open autonomous driving platform

hailanyi.

ONCE_Benchmark. One Million Scenes for Autonomous Driving

FedGS. FedGS: Federated Graph-based Sampling with Arbitrary Client Availability, arxiv.org/abs/2211.13975) was accepted by AAAI 2023 Conference.

easyFL. An experimental platform for federated learning.

SMPL-Scene-Viewer. A simple and fast GUI tool to visualize and compare the SMPL sequences and scenes in real-time.

consensus-maddpg. Python

music-generation. Comparison of methods (VAE, Bi-LSTM, baseline-LSTM) for jazz music generation.

HSC4D. HSC4D: Human-centered 4D Scene Capture in Large-scale Indoor-outdoor Space Using Wearable IMUs and LiDAR. CVPR 2022

TransFusion. [PyTorch] Official implementation of CVPR2022 paper "TransFusion: Robust LiDAR-Camera Fusion for 3D Object Detection with Transformers". https://arxiv.org/abs/2203.11496

3D-Detection-Tracking-Viewer. 3D detection and tracking viewer (visualization) for kitti & waymo dataset

VPFNet. Python

GraphRCNN. Graph R-CNN: Towards Accurate 3D Object Detection with Semantic-Decorated Local Graph (ECCV 2022, Oral) :fire:

Voxel-R-CNN. Python

SFD. Sparse Fuse Dense: Towards High Quality 3D Detection with Depth Completion (CVPR 2022, Oral)

Awesome-3D-Detectors. Paperlist of awesome 3D detection methods

mmdetection. OpenMMLab Detection Toolbox and Benchmark

HowToCook. Programmer's guide about how to cook at home.

CasA. A Cascade Attention Network for 3D Object Detection from LiDAR point clouds

awesome-3d-object-detection. Awesome 3d object detection paper, code and note

dair_v2x_i_dataset_vis. For visualizing the dair-v2x-i dataset

pytorch-CycleGAN-and-pix2pix. Image-to-Image Translation in PyTorch

MYC_Web_Server. 很简单的 Web_server 项目，不断地实现项目功能中

Learning_Project. 设计模式、TCP高并发服务器、HTTP连接、DNS查询、DNS异步I/O查询实现、多线程实现、线程池实现、MySql使用、MySql连接池实现、通讯录实现

RBtree-Btree. 二叉树，B树，红黑树的实现

InsightFace_Pytorch. Pytorch0.4.1 codes for InsightFace

TinyWebServer. :fire: Linux下C++轻量级Web服务器

LeetCode. 记录刷LeetCode的过程，解题过程或官方或自己。

Sylar. Reprinted from https://github.com/sylar-yin/sylar

TimerWheel-TimerHeap. 对时间轮等定时器的学习和实现。并熟悉最小堆数据结构

High-Performance-Linux-Server-Programming. 服务器编程学习

LearningCode. 备份一些自己的代码，电脑坏两次导致心态崩了

OAMN. Python

3d-bat. 3D Bounding Box Annotation Tool (3D-BAT) Point cloud and Image Labeling

Swin-Transformer. This is an official implementation for "Swin Transformer: Hierarchical Vision Transformer using Shifted Windows".

CT3D. "Improving 3D Object Detection with Channel-wise Transformer", ICCV2021 accept!

2018--ZJUAI--PyramidBoxDetector. 2018 云从人头技术冠军分享方案

LearningToCompare_ZSL. PyTorch code for CVPR 2018 paper: Learning to Compare: Relation Network for Few-Shot Learning (Zero-Shot Learning part)

kitti360LabelTool. JavaScript

CasTrack-waymo. Online 3D multi-object tracking on Waymo dataset

DeepLearning. TeX

latte. LATTE: Accelerating LiDAR Point Cloud Annotation via Sensor Fusion, One-Click Annotation, and Tracking

bat-3d. 3D Bounding Box Annotation Tool 2.0 (3D-BAT 2.0): Labeling of 3D LiDAR Point Clouds and Camera Images

mean-teacher. A state-of-the-art semi-supervised method for image recognition

PointFlow. PointFlow : 3D Point Cloud Generation with Continuous Normalizing Flows

3D-Multi-Object-Tracker. A project for 3D multi-object tracking

Cylinder3D. Rank 1st in the leaderboard of SemanticKITTI semantic segmentation (both single-scan and multi-scan) (Nov. 2020) (CVPR2021 Oral)

lanoising. Python

spconv. Spatial Sparse Convolution Library

waymo-open-dataset. Waymo Open Dataset

OpenPCDet. OpenPCDet Toolbox for LiDAR-based 3D Object Detection.

TANet. The AAAI-2020 Paper(Oral):"TANet: Robust 3D Object Detection from Point Clouds with Triple Attention"

CenterPoint. Python