[ICRA2024] Towards Motion Forecasting with Real-World Perception Inputs: Are End-to-End Approaches Competitive? This is the official implementation of the evaluation protocol proposed in this work …

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

PillarNeXt: Rethinking Network Designs for 3D Object Detection in LiDAR Point Clouds (CVPR 2023)

VectorNet: Encoding HD Maps and Agent Dynamics from Vectorized Representation, partial function re-implement

Pip package for the CVPRW 2023 Paper "Lanelet2 for nuScenes: Enabling Spatial Semantic Relationships and Diverse Map-Based Anchor Paths".

MTR: Motion Transformer with Global Intention Localization and Local Movement Refinement, NeurIPS 2022.

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

Simple visualization of NGSIM I-80 dataset

[CVPR 2023] Official repository for FJMP: Factorized Joint Multi-Agent Motion Prediction

MonoLayout: Amodal Scene Layout from a single image

A playbook for systematically maximizing the performance of deep learning models.

Forecasting from LiDAR via Future Object Detection. CVPR '22

Official implementation of the ITSC 2023 paper "LiDAR View Synthesis for Robust Vehicle Navigation Without Expert Labels"

Official Code Release of "FusionAD"

Vehicle Trajectory Prediction with Deep Learning Models

A Simple PointPillars PyTorch Implementation for 3D LiDAR(KITTI) Detection.

Papers and Datasets about Point Cloud.