nuscenes

SECOND for KITTI/NuScenes object detection

A general 3D object detection codebse.

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

Code accompanying the ECCV 2020 paper "Trajectron++: Dynamically-Feasible Trajectory Forecasting With Heterogeneous Data" by Tim Salzmann*, Boris Ivanovic*, Punarjay Chakravarty, and Marco Pavone (* denotes equal contribution).

[WACV2022] ImVoxelNet: Image to Voxels Projection for Monocular and Multi-View General-Purpose 3D Object Detection

Exploring Simple 3D Multi-Object Tracking for Autonomous Driving (ICCV 2021)

Papers on 3D Object Detection for Autonomous Driving

Self-Supervised Pillar Motion Learning for Autonomous Driving (CVPR 2021)

Code for Langer et al. "Domain Transfer for Semantic Segmentation of LiDAR Data using Deep Neural Networks", IROS, 2020.

This repository provides awesome research papers for autonomous driving perception. If you do find a problem or have any suggestions, please raise this as an issue or make a pull request with information (format of the repo): Research paper title, datasets, metrics, objects, source code, publisher, and year.

Code for "Multimodal Trajectory Prediction Conditioned on Lane-Graph Traversals," CoRL 2021.

A tool to visualize nuscenes format dataset in 3D using mayavi

A New 3D Detector. Code Will be made public.

Trajectory Prediction with Local Self-Attentive Contexts for Autonomous Driving (NeurIPS 2020)

This repo parallelizes mAP_evaluation using python's multiprocessing module.

Conversion of NuScenes auto driving dataset to KITTI format

3D Multi-Object Tracking Using Graph Neural Networks with Cross-Edge Modality Attention. http://batch3dmot.cs.uni-freiburg.de

3D object detection on the nuScenes dataset

Fusion of LiDAR and depth camera data with deep learning for object detection and classification

Lane detection program (Python) for the nuScenes mini dataset

object detection

CenterFusion++ is a frustum propsal-based camera and radar sensor fusion network.

nuScenes pose expansion in ROS msg

Fast 3D Object Detection in the Wild

Moving vehicle detection system that focusses on clustering and uses the capabilities of existing vision approaches.