Official implentation of "Ghost on the Shell: An Expressive Representation of General 3D Shapes" (ICLR 2024 Oral)

cloth2tex, 3D textured virtual Try-On, 3DV 2024

Refine high-quality datasets and visual AI models

Code Repository for CVPR 2023 Paper "PanoHead: Geometry-Aware 3D Full-Head Synthesis in 360 degree"

InstantAvatar: Learning Avatars from Monocular Video in 60 Seconds (CVPR 2023)

[ICCV 2023] Make-It-3D: High-Fidelity 3D Creation from A Single Image with Diffusion Prior

Segment Anything in High Quality [NeurIPS 2023]

4DHumans: Reconstructing and Tracking Humans with Transformers

Unofficial Implementation of DragGAN - "Drag Your GAN: Interactive Point-based Manipulation on the Generative Image Manifold" （DragGAN 全功能实现，在线Demo，本地部署试用，代码、模型已全部开源，支持Windows, macOS, Linux）

The source code of ECCV18 'Flow-Grounded Spatial-Temporal Video Prediction from Still Images'.

Code for "AutoRecon: Automated 3D Object Discovery and Reconstruction" CVPR 2023 (Highlight)

A unified framework for 3D content generation.

[CVPR 2023] Official repository for downloading, processing, visualizing, and training models on the ARCTIC dataset.

PyTorch implementation of the ICCV paper "3D-aware Image Generation using 2D Diffusion Models"

为GPT/GLM等LLM大语言模型提供实用化交互接口，特别优化论文阅读/润色/写作体验，模块化设计，支持自定义快捷按钮&函数插件，支持Python和C++等项目剖析&自译解功能，PDF/LaTex论文翻译&总结功能，支持并行问询多种LLM模型，支持chatglm3等本地模型。接入通义千问, deepseekcoder, 讯飞星火, 文心一言, llama2, rwkv, claude2, m…

Vid2Avatar: 3D Avatar Reconstruction from Videos in the Wild via Self-supervised Scene Decomposition (CVPR2023)

Official implementation of "Composer: Creative and Controllable Image Synthesis with Composable Conditions"

CUDA Mesh BVH tools.

[ICCV 2023] One-shot Implicit Animatable Avatars with Model-based Priors

Cuda implementation for gridsample with second derivative support

A Unified Framework for Surface Reconstruction

Official implementation and data release of the paper "Visual Prompting via Image Inpainting".

Fast and Differentiable Meshing of Unsigned Distance Field Networks

Stable Diffusion web UI

Code for "MeuMesh: Learning Disentangled Neural Mesh-based Implicit Field for Geometry and Texture Editing", ECCV 2022 Oral

[NeurIPS 2022] Official pytorch implementation of EpiGRAF

A set of tools to visualize and interact with sequences of 3D data.

[SIGGRAPH 2022 Journal Track] AvatarCLIP: Zero-Shot Text-Driven Generation and Animation of 3D Avatars

Improved diffusion generative models with subspaces