OccSora: 4D Occupancy Generation Models as World Simulators for Autonomous Driving

Introduce Multiscope Conception to Sequential Descision Learning

Source code of PivotNet (ICCV2023, PivotNet: Vectorized Pivot Learning for End-to-end HD Map Construction)

[CVPR 2024 Award Candidate] Producing and Leveraging Online Map Uncertainty in Trajectory Prediction

D-FINE: Redefine Regression Task of DETRs as Fine-grained Distribution Refinement 💥💥💥

Collect some World Models for Autonomous Driving papers.

Layout-Guided multi-view driving scene video generation with latent diffusion model

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

Next-Token Prediction is All You Need

This is a collective repository for all 3DGS related progresses in research and industry world

CUDA accelerated rasterization of gaussian splatting

PyTorch Code for Neural MP: A Generalist Neural Motion Planner

Hybrid A* Path Planner for the KTH Research Concept Vehicle

RoGs: Large Scale Road Surface Reconstruction with Meshgrid Gaussian

Multiple Object Tracking as ID Prediction

[CVPR2024] Official Repository of Paper "Panacea: Panoramic and Controllable Video Generation for Autonomous Driving"

[RA-L] DreamCar: Leveraging Car-specific Prior for in-the-wild 3D Car Reconstruction

[ECCV 2024] This is the official implementation of Learning High-resolution Vector Representation from Multi-Camera Images for 3D Object Detection.

VGGSfM: Visual Geometry Grounded Deep Structure From Motion

Segment Anything in 3D with NeRFs (NeurIPS 2023)

Implementation of "Learning to Make Keypoints Sub-Pixel Accurate" (ECCV 2024).

Official Implementation of A Vision-Centric Approach for Static Map Element Annotation

[ICRA 2024] Differentiable Joint Conditional Prediction and Cost Evaluation for Tree Policy Planning

[T-ITS] Driving Behavior Modeling using Naturalistic Human Driving Data with Inverse Reinforcement Learning

PyTorch native quantization and sparsity for training and inference

[ECCV'24] SeFlow: A Self-Supervised Scene Flow Method in Autonomous Driving