SOTA Semantic Segmentation Models in PyTorch

Semantic Segmentation in Pytorch. Network include: FCN、FCN_ResNet、SegNet、UNet、BiSeNet、BiSeNetV2、PSPNet、DeepLabv3_plus、 HRNet、DDRNet

The official implementation of "Deep Dual-resolution Networks for Real-time and Accurate Semantic Segmentation of Road Scenes"

Code release for "Masked-attention Mask Transformer for Universal Image Segmentation"

LSD (LiDAR SLAM & Detection) is an open source perception architecture for autonomous vehicle/robotic

3D Object Detection Visualization tool based on mayavi

KITTI Object Visualization (Birdview, Volumetric LiDar point cloud )

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

Web labeling tool for bitmap images and point clouds

3D Point Cloud Annotation Platform for Autonomous Driving

[RAL & IROS 2022] Lidar With Velocity: Correcting Moving Objects Point Cloud Distortion From Oscillating Scanning Lidars by Fusion With Camera

This project is used for lidar point cloud undistortion.

OpenPCDet Toolbox for LiDAR-based 3D Object Detection.

Magnificent app which corrects your previous console command.

[Information Fusion 2025] A Survey on Occupancy Perception for Autonomous Driving: The Information Fusion Perspective

[ICCV 2023] SurroundOcc: Multi-camera 3D Occupancy Prediction for Autonomous Driving

[ICCV 2023] OccNet: Scene as Occupancy

3D occupancy

《深度学习入门-基于Python的理论与实现》，包含源代码和高清PDF(带书签)；慕课网imooc《深度学习之神经网络(CNN-RNN-GAN)算法原理-实战》；《菜菜的机器学习sklearn》

Official Code Release of "FusionAD"

Bridging Large Vision-Language Models and End-to-End Autonomous Driving

[ICCV 2023] VAD: Vectorized Scene Representation for Efficient Autonomous Driving

Sky-T1: Train your own O1 preview model within $450

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

Code for paper "MapTracker: Tracking with Strided Memory Fusion for Consistent Vector HD Mapping", ECCV 2024 (Oral)

[NeurIPS 2024] A Generalizable World Model for Autonomous Driving

[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.

[ECCV 2024] This is the official implementation of HRMapNet, maintaining and utilizing a low-cost global rasterized map to enhance online vectorized map perception.