[CVPR 2022] "MonoScene: Monocular 3D Semantic Scene Completion": 3D Semantic Occupancy Prediction from a single image

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

[CVPR 2023] An academic alternative to Tesla's occupancy network for autonomous driving.

[ICCV 2023] OpenOccupancy: A Large Scale Benchmark for Surrounding Semantic Occupancy Perception

CVPR2023-Occupancy-Prediction-Challenge

[ICRA 2022] An opensource framework for cooperative detection. Official implementation for OPV2V.

Virtual Sparse Convolution for Multimodal 3D Object Detection

Transformation-Equivariant 3D Object Detection for Autonomous Driving

We proposed a large-scale benchmark for traffic accidents detection from video surveillance

3D occupancy

Vision-Centric BEV Perception: A Survey

Awesome papers about Multi-Camera 3D Object Detection and Segmentation in Bird's-Eye-View, such as DETR3D, BEVDet, BEVFormer, BEVDepth, UniAD

Feature tracking and (monocular) visual odometry using KITTI dataset

pySLAM is a visual SLAM pipeline in Python for monocular, stereo and RGBD cameras. It supports many modern local and global features, different loop-closing methods, a volumetric reconstruction pip…

Fast-Feature-Detector

Baselines for the Image Matching Benchmark and Challenge

A framework for local feature evaluation for Python and MATLAB.

Code for "LoFTR: Detector-Free Local Feature Matching with Transformers", CVPR 2021, T-PAMI 2022

Repository for "TILDE: A Temporally Invariant Learned DEtector", CVPR2015

This is the official implementation in PyTorch for AAAI2022 paperGuide Local Feature Matching by Overlap Estimation and also contain a image matching toolbox.

[ICCV 2019] Key.Net: Keypoint Detection by Handcrafted and Learned CNN Filters - PyTorch

[ECCV'20] Convolutional Occupancy Networks

🔥OGC in PyTorch (NeurIPS 2022 & TPAMI 2024)

4个不同方向的相机，将其鸟瞰变化后，进行拼接，得到车辆及周围区域的鸟瞰视角图 Put FOUR image(or video stream) from 4 different directions together, and form them into a bird view.

(3DV 2021) A High-fidelity 128-channel LiDAR Dataset with Panoramic Ambient and Reflectivity Imagery for Multi-modal Autonomous Driving Applications

Toolkit to convert a clean LiDAR-camera dataset into a robustness benchmark

Some Conferences' accepted paper lists (including AI, ML, Robotic)

Semi-supervised Implicit Scene Completion from Sparse LiDAR

Official PyTorch Implementation of Neural Feature Fusion Fields: 3D Distillation of Self-Supervised 2D Image Representations