-
CyberAgent AI Lab
- Tokyo, Japan
- https://xucao-42.github.io/homepage/
- @Xu_Cao_
Stars
Official implementation of Continuous 3D Perception Model with Persistent State
Open source impl of **MV-DUSt3R+ Single-Stage Scene Reconstruction from Sparse Views In 2 Seconds** from Meta Reality Labs. Project page https://mv-dust3rp.github.io/
[CVPR 2024 Highlight] The official repo for "GaussianAvatars: Photorealistic Head Avatars with Rigged 3D Gaussians"
Continuous Remeshing For Inverse Rendering
Code for the project "MegaSaM: Accurate, Fast and Robust Structure and Motion from Casual Dynamic Videos"
Original implementation of "3D Convex Splatting: Radiance Field Rendering with 3D Smooth Convexes"
[SIGGRAPH Asia 2024, Best Paper Honorable Mention] This is the official implementation of our SIGGRAPH Asia journal artical: TEXGen: a Generative Diffusion Model for Mesh Textures
A collection of papers on diffusion models for 3D generation.
Calculate signed distance fields for arbitrary meshes
[3DV 2025] Official Implementation of paper "Photometric Inverse Rendering: Shading Modeling and Surface Reflectance Regularization"
Official Implementation of paper "MonST3R: A Simple Approach for Estimating Geometry in the Presence of Motion"
Resources Related to Event-based Vision | Event Cameras | DVS
[SIGGRAPH Asia 2024 (Journal Track)] StableNormal: Reducing Diffusion Variance for Stable and Sharp Normal
Source code for "Differentiable Signed Distance Function Rendering" (Siggraph 2022)
[SIGGRAPH Asia 2024] PuzzleAvatar: Assembling 3D Avatars from Personal Albums
YuliangXiu / StableNormal-1
Forked from Stable-X/StableNormal[SIGGRAPH Asia 2024 & TOG] StableNormal: Reducing Diffusion Variance for Stable and Sharp Normal
[ECCV2024] Relightable 3D Gaussian: Real-time Point Cloud Relighting with BRDF Decomposition and Ray Tracing
point-light photometric stereo for metal surface reconstruction
[CVPR 2024✨Highlight] Official repository for HOLD, the first method that jointly reconstructs articulated hands and objects from monocular videos without assuming a pre-scanned object template and…
An open-source impl. of Large Reconstruction Models
[SIGGRAPH'24] 2D Gaussian Splatting for Geometrically Accurate Radiance Fields
Implementation of the SIGGRAPH 2024 conference paper "High-quality Surface Reconstruction using Gaussian Surfels".