A Unreal Engine 5 (UE5) based plugin aiming to provide real-time visulization, management, editing, and scalable hybrid rendering of Guassian Splatting model.

3DGS-to-PC: Convert a 3D gaussian splatting scene into a dense point cloud or basic mesh with advanced customisation options and high-accuracy rendered point colours

SplaTAM: Splat, Track & Map 3D Gaussians for Dense RGB-D SLAM (CVPR 2024)

Open source Structure-from-Motion pipeline

[CVPR'24 Highlight & Best Demo Award] Gaussian Splatting SLAM

A unified framework for 3D content generation.

3D Gaussian Splatting extension of threestudio.

Gaussian-SLAM: Photo-realistic Dense SLAM with Gaussian Splatting

[3DV 2025] LoopSplat: Loop Closure by Registering 3D Gaussian Splats

3D Gaussian Splatting Converter: A tool to seamlessly convert 3DGS .ply files to a Cloud Compare-friendly format and vice-versa. Features include RGB coloring, density filtering, and flyer removal …

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

Photo-realistic mapping of dynamic urban areas

[CVPR2024] NeuRAD: Neural Rendering for Autonomous Driving

Official implementation of the SIGGRAPH 2024 paper "A Hierarchical 3D Gaussian Representation for Real-Time Rendering of Very Large Datasets"

This repository contains the PyTorch implementation of the CVPR'2024 paper (Highlight), IS-Fusion: Instance-Scene Collaborative Fusion for Multimodal 3D Object Detection.

[CVPR 2024 Oral] Rethinking Inductive Biases for Surface Normal Estimation

[CVPR 2024] Official PyTorch implementation of SuGaR: Surface-Aligned Gaussian Splatting for Efficient 3D Mesh Reconstruction and High-Quality Mesh Rendering

DN-Splatter + AGS-Mesh: Depth and Normal Priors for Gaussian Splatting

CUDA accelerated rasterization of gaussian splatting

Official Implementation of Self-Supervised Street Gaussians for Autonomous Driving

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

3D Bounding Box Annotation Tool (3D-BAT) Point cloud and Image Labeling

[ICLR 2024 Spotlight] SyncDreamer: Generating Multiview-consistent Images from a Single-view Image

[ECCV2024 Oral] Clearer anytime frame interpolation & Manipulated interpolation of anything

Code for a series of work in LiDAR perception, including SST (CVPR 22), FSD (NeurIPS 22), FSD++ (TPAMI 23), FSDv2, and CTRL (ICCV 23, oral).

A project demonstrating Lidar related AI solutions, including three GPU accelerated Lidar/camera DL networks (PointPillars, CenterPoint, BEVFusion) and the related libs (cuPCL, 3D SparseConvolution…

An easy to use PyTorch to TensorRT converter

A simple tool that can generate TensorRT plugin code quickly.

Presentation Slides for Developers

Segment-Anything + 3D. Let's lift anything to 3D.