[CVPR2022] Geometric Transformer for Fast and Robust Point Cloud Registration

WinDivert: Windows Packet Divert

OpenVDB - Sparse volume data structure and tools

A Parallel Fluid Solver and Renderer on the GPU

Multi-threaded, CPU-based vector graphics rasterizer.

Offical code for "FastGS: Training 3D Gaussian Splatting in 100 Seconds"

Low overhead tracing library and trace visualizer for pipelined CUDA kernels

(ICRA 2025) LiLoc: Lifelong Localization using Adaptive Submap Joining and Egocentric Factor Graph

simple immediate lightweight tensors

code release for HouseCrafter (ICCV 2025 Highlight)

Blind&Invisible Watermark ，图片盲水印，提取水印无须原图！

View Transformation Robustness for Multi-View 3D Object Reconstruction with Reconstruction Error-Guided View Selection, AAAI 25

This is the code repository implementing the paper "TreePartNet: Neural Decomposition of Point Clouds for 3D Tree Reconstruction".

[ECCV 2024] FRI-Net: Floorplan Reconstruction via Room-wise Implicit Representation

A Dynamic-Aware LIO Framework Via Spatio-Temporal Normal Analysis

StreamingVLM: Real-Time Understanding for Infinite Video Streams

Contexts Optical Compression

Public repository for Skills

SD.Next: All-in-one WebUI for AI generative image and video creation

SD.Next ModernUI

✨ WithAnyone is capable of generating high-quality, controllable, and ID consistent images

A procedural Blender pipeline for photorealistic training image generation

[SIGGGRAPHASIA2025] PhySIC: Physically Plausible 3D Human-Scene Interaction and Contact from a Single Image

[SIGGRAPH Asia 2025] "ASIA: Adaptive 3D Segmentation using Few Image Annotations ".

PhoCoLens: Photorealistic and Consistent Reconstruction in Lensless Imaging

Orillusion is a pure Web3D rendering engine which is fully developed based on the WebGPU standard.