[NeurIPSW 2023] The "cleaned" version of CelebA-HQ and Flickr-Faces-HQ.

[NeurIPS 2024] Generalizable and Animatable Gaussian Head Avatar

🤏🏻 `investpy` but made tiny

The Official PyTorch Implementation of "NVAE: A Deep Hierarchical Variational Autoencoder" (NeurIPS 2020 spotlight paper)

[CVPR 2024] Official repository for "Gaussian Head Avatar: Ultra High-fidelity Head Avatar via Dynamic Gaussians"

TriplaneGaussian: A new hybrid representation for single-view 3D reconstruction.

Official Code Base of the Paper: "Joker: Conditional 3D Head Synthesis with Extreme Facial Expressions"

[NeurIPS 2024] Generalizable and Animatable Gaussian Head Avatar

[SIGGRAPH ASIA '24] GGHead: Fast and Generalizable 3D Gaussian Heads

Official Codebase of "DiffComplete: Diffusion-based Generative 3D Shape Completion"

macOS system monitor in your menu bar

3D U-Net model for volumetric semantic segmentation written in pytorch

Rendering color and depth images for ShapeNet models.

This is a implementation of the 3D FLAME model in PyTorch

Official code for "FeatUp: A Model-Agnostic Frameworkfor Features at Any Resolution" ICLR 2024

The repository provides code for running inference with the SegmentAnything Model (SAM), links for downloading the trained model checkpoints, and example notebooks that show how to use the model.

[ICCV'23 Workshop] SAM3D: Segment Anything in 3D Scenes

Official pytorch implementation of "Self-positioning Point-based Transformer for Point Cloud Understanding" (CVPR 2023).

FaRL for Facial Representation Learning [Official, CVPR 2022]

PartNet Shape Segmentation Experiments Code Repo

This is the official code for "Learning Multi-Resolution Patch Priors for 3D Shape Completion on Unseen Categories"

Minkowski Engine is an auto-diff neural network library for high-dimensional sparse tensors

macOS Picture in Picture and AirPlay Receiver

Official implementation of the NeurIPS 2021 paper "Panoptic 3D Scene Reconstruction from a Single RGB Image"

Minkowski Engine is an auto-diff neural network library for high-dimensional sparse tensors

[CVPR 2023] Diffusion-SDF: Text-to-Shape via Voxelized Diffusion

ProlificDreamer: High-Fidelity and Diverse Text-to-3D Generation with Variational Score Distillation (NeurIPS 2023 Spotlight)

(ICCV2023) official repository for "Fantasia3D: Disentangling Geometry and Appearance for High-quality Text-to-3D Content Creation"