Cosmos is a world model development platform that consists of world foundation models, tokenizers and video processing pipeline to accelerate the development of Physical AI at Robotics & AV labs. C…

Light-field imaging application for plenoptic cameras

A framework to convert any 2D videos to immersive stereoscopic 3D

[NeurIPS 23] Official repository for NeurIPS 2023 paper "Global-correlated 3D-decoupling Transformer for Clothed Avatar Reconstruction"

IDOL: Instant Photorealistic 3D Human Creation from a Single Image. An open-source project for fast, high-fidelity, and generalizable 3D human reconstruction from a single image.

GenXD: Generating Any 3D and 4D Scenes

Official repository for the paper "CAP4D: Creating Animatable 4D Portrait Avatars with Morphable Multi-View Diffusion Models"

You See it, You Got it: Learning 3D Creation on Pose-Free Videos at Scale

AutoLens: automated lens design from scratch.

PanoDreamer: 3D Panorama Synthesis from a Single Image

AniGS: Animatable Gaussian Avatar from a Single Image with Inconsistent Gaussian Reconstruction

HunyuanVideo: A Systematic Framework For Large Video Generation Model

Code for our ICCV'2023 paper "SHERF: Generalizable Human NeRF from a Single Image"

We present StableAnimator, the first end-to-end ID-preserving video diffusion framework, which synthesizes high-quality videos without any post-processing, conditioned on a reference image and a se…

[SIGGRAPH'24] CharacterGen: Efficient 3D Character Generation from Single Images with Multi-View Pose Canonicalization

DRiVE: Diffusion-based Rigging Empowers Generation of Versatile and Expressive Characters

Consistent Human Image and Video Generation with Spatially Conditioned Diffusion

Lumina-T2X is a unified framework for Text to Any Modality Generation

[WACV 2025] Official implementation of "RAW-Diffusion: RGB-Guided Diffusion Models for High-Fidelity RAW Image Generation"

Official code for the paper "SplatFlow: Multi-View Rectified Flow Model for 3D Gaussian Splatting Synthesis"

Official Implementation of Our Paper "X as Supervision: Contending with Depth Ambiguity in Unsupervised Monocular 3D Pose Estimation"

Subjects200K dataset

Code of [CVPR 2024] "Animatable Gaussians: Learning Pose-dependent Gaussian Maps for High-fidelity Human Avatar Modeling"

DimensionX: Create Any 3D and 4D Scenes from a Single Image with Controllable Video Diffusion

A suite of image and video neural tokenizers

Official PyTorch implementation of "Framer: Interactive Frame Interpolation".