A 3DGS framework for omni urban scene reconstruction and simulation.

GaussianOcc: Fully Self-supervised and Efficient 3D Occupancy Estimation with Gaussian Splatting

[CSUR 2023] A Survey on Deep Generative 3D-aware Image Synthesis

[Preprint] OneFormer: One Transformer to Rule Universal Image Segmentation, 2022

Repository for Show-o, One Single Transformer to Unify Multimodal Understanding and Generation.

[ECCV 2024] Implementation of latentSplat: Autoencoding Variational Gaussians for Fast Generalizable 3D Reconstruction

Autoregressive Model Beats Diffusion: 🦙 Llama for Scalable Image Generation

Official repository of ”LION: Linear Group RNN for 3D Object Detection in Point Clouds“

Official code implementation of Vary-toy (Small Language Model Meets with Reinforced Vision Vocabulary)

UniPAD: A Universal Pre-training Paradigm for Autonomous Driving (CVPR 2024)

Collect some World Models for Autonomous Driving papers.

🤗 Diffusers: State-of-the-art diffusion models for image and audio generation in PyTorch and FLAX.

InstantMesh: Efficient 3D Mesh Generation from a Single Image with Sparse-view Large Reconstruction Models

Point cloud diffusion for 3D model synthesis

Generate 3D objects conditioned on text or images

Photo-realistic mapping of dynamic urban areas

Official Implementation of Self-Supervised Street Gaussians for Autonomous Driving

🕷️ SpiderMatch: 3D Shape Matching with Global Optimality and Geometric Consistency

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

NeuroNCAP benchmark for end-to-end autonomous driving

[SIGGRAPH'24] 2D Gaussian Splatting for Geometrically Accurate Radiance Fields

Fully Sparse Transformer 3D Detector for LiDAR Point Cloud

[ICRA 2024] Lightning NeRF: Efficient Hybrid Scene Representation for Autonomous Driving

[CVPR 2024] 4D Gaussian Splatting for Real-Time Dynamic Scene Rendering

本人的科研经验

[ECCV 2024] Street Gaussians: Modeling Dynamic Urban Scenes with Gaussian Splatting

[CVPR 2024] LMDrive: Closed-Loop End-to-End Driving with Large Language Models

[CVPR2024] NeuRAD: Neural Rendering for Autonomous Driving