RaDe-GS: Rasterizing Depth in Gaussian Splatting

The official implementation of CVPR'26 paper "Lighting in Motion: Spatiotemporal HDR Lighting Estimation"

Perfect Green Screen Keys

Official code for CVPR 2026 paper: VGGT-Det: Mining VGGT Internal Priors for Sensor-Geometry-Free Multi-View Indoor 3D Object Detection

A refactored codebase for Gaussian Splatting. Training 3DGS in 50 seconds!

Sharp Monocular View Synthesis in Less Than a Second

Depth Anything 3

This repository contains the implementation of our novel approach associated with the paper "Don't Splat Your Gaussians" to modeling and rendering scattering and emissive media using volumetric pri…

FaceXlib aims at providing ready-to-use face-related functions based on current STOA open-source methods.

[SIGGRAPH Asia 2025] 4DSloMo: 4D Reconstruction for High Speed Scene with Asynchronous Capture

Tensors and Dynamic neural networks in Python with strong GPU acceleration

3FUI 是 ffmpeg 在 Windows 上的轻度专业交互外壳，收录大量参数，界面美观，交互友好。此项目面向国内使用环境，让普通人也能够轻松压制视频和转换格式。

Video datasets

[CVPR 2025 Oral & Best Paper Finalist] Difix3D+: Improving 3D Reconstructions with Single-Step Diffusion Models

Code for the project "MegaSaM: Accurate, Fast and Robust Structure and Motion from Casual Dynamic Videos"

[CVPR 2025 Best Paper Nomination] FoundationStereo: Zero-Shot Stereo Matching

Fast, accurate and easy to run dense optical flow with python wrapper

Mixbox is a library for natural color mixing based on real pigments.

Ray tracing and hybrid rasterization of Gaussian particles

SkyReels V1: The first and most advanced open-source human-centric video foundation model

Gaussian Splatting Operators for SideFX Houdini

HunyuanVideo: A Systematic Framework For Large Video Generation Model

The official implementation of CVPR'25 Oral paper "Go-with-the-Flow: Motion-Controllable Video Diffusion Models Using Real-Time Warped Noise"

RayGauss: Volumetric Gaussian-Based Ray Casting for Photorealistic Novel View Synthesis

[SIGGRAPH Asia'24 & TOG] Gaussian Opacity Fields: Efficient Adaptive Surface Reconstruction in Unbounded Scenes

Simulation platform for general-purpose robotics & embodied AI learning.

Implementation of UltraPixel: Advancing Ultra-High-Resolution Image Synthesis to New Peaks

ResShift: Efficient Diffusion Model for Image Super-resolution by Residual Shifting (NeurIPS@2023 Spotlight, TPAMI@2024)