From anything to mesh like human artists. Official impl. of "MeshAnything: Artist-Created Mesh Generation with Autoregressive Transformers"

Implementation of the SIGGRAPH 2024 conference paper "High-quality Surface Reconstruction using Gaussian Surfels".

[CVPR 2024] Sparse Global Matching for Video Frame Interpolation with Large Motion

The Devil is in the Edges: Monocular Depth Estimation with Edge-aware Consistency Fusion

StreamingT2V: Consistent, Dynamic, and Extendable Long Video Generation from Text

An extensive node suite that enables ComfyUI to process 3D inputs (Mesh & UV Texture, etc) using cutting edge algorithms (3DGS, NeRF, etc.)

An Open Source 3d character and character controller for the Godot game engine

DreamUV - 3D viewport UV editing tools for Blender

A High Performance Compute Shader Based Mesh Pathtracer in Unity3d without RT Cores

Godot Jolt is a Godot extension that integrates the Jolt physics engine

Blender addon that simplifies access to useful operators and adds missing functionality

Official implementation of "En3D: An Enhanced Generative Model for Sculpting 3D Humans from 2D Synthetic Data"

A multi-voice TTS system trained with an emphasis on quality

text and image to video generation: CogVideoX (2024) and CogVideo (ICLR 2023)

Official code for the CVPR 2022 (oral) paper "Extracting Triangular 3D Models, Materials, and Lighting From Images".

Instant neural graphics primitives: lightning fast NeRF and more

High Quality Monocular Depth Estimation via Transfer Learning

Implementation of NÜWA, state of the art attention network for text to video synthesis, in Pytorch

GLIDE: a diffusion-based text-conditional image synthesis model

Minimalistic DeepDream with C89

Plenoxels: Radiance Fields without Neural Networks

Retro coding in C/C++ in a 3D template with full low-level control.

Modifications of the official PyTorch implementation of StyleGAN3. Let's easily generate images and videos with StyleGAN2/2-ADA/3!

Code for "HyperNeRF: A Higher-Dimensional Representation for Topologically Varying Neural Radiance Fields".

PyTorch implementations for our SIGGRAPH 2021 paper: Editable Free-viewpoint Video Using a Layered Neural Representation.