Lane detection with PaddlePaddle. PPLanedet contains many SOTA methods, e.g. CondLaneNet, SCNN, RESA, RTFormer,UFLD

Official PyTorch implementation of "UrbanIR: Large-Scale Urban Scene Inverse Rendering from a Single Video"

DifFUSER: Diffusion Model for Robust Multi-Sensor Fusion in 3D Object Detection and BEV Segmentation

[ECCV 2024] SplatFields: Neural Gaussian Splats for Sparse 3D and 4D Reconstruction

[ICCV 2023] StableVideo: Text-driven Consistency-aware Diffusion Video Editing

[TVCG2024] PGSR: Planar-based Gaussian Splatting for Efficient and High-Fidelity Surface Reconstruction

RoGS: Large Scale Road Surface Reconstruction based on 2D Gaussian Splatting

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

Video-P2P: Video Editing with Cross-attention Control

OpenMMLab's Next Generation Video Understanding Toolbox and Benchmark

[NeurIPS'24] WildGaussians: 3D Gaussian Splatting In the Wild

[ECCV 2024] Efficient Large-Baseline Radiance Fields, a feed-forward 2DGS model

RaDe-GS: Rasterizing Depth in Gaussian Splatting

🧙🏻‍♂️A list of papers curated for you to dive into the Awesome Radiance Field-based 3D Editing.

[CVPR 2024] code release for "DiffusionLight: Light Probes for Free by Painting a Chrome Ball"

Official code for "Neural Gaffer: Relighting Any Object via Diffusion"

[ECCV2024] Relightable 3D Gaussian: Real-time Point Cloud Relighting with BRDF Decomposition and Ray Tracing

The PyTorch implementation of ICCV 2019 oral paper: free-form inpainting (deepfillv2), especially Gated Conv

The offical code repository for SC-4DGS.

Photo-realistic mapping of dynamic urban areas

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

3D高斯论文，持续更新，欢迎交流讨论。

[CVPR 2024 Highlight] Scaffold-GS: Structured 3D Gaussians for View-Adaptive Rendering

[ICLR 2024 Oral] Generative Gaussian Splatting for Efficient 3D Content Creation

Official repository of NeuMan: Neural Human Radiance Field from a Single Video (ECCV 2022)

Official Implementation of Self-Supervised Street Gaussians for Autonomous Driving

GaussianObject: High-Quality 3D Object Reconstruction from Four Views with Gaussian Splatting (SIGGRAPH Asia 2024, TOG)

[CVPR 2024] Official implementation of "Deformable 3D Gaussians for High-Fidelity Monocular Dynamic Scene Reconstruction"

Unofficial implementation of "Street Gaussians: Modeling Dynamic Urban Scenes with Gaussian Splatting", ECCV2024.