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…

Uncommon Objects in 3D dataset

[CVPR'24] Official PyTorch Implementation of "Paint-it: Text-to-Texture Synthesis via Deep Convolutional Texture Map Optimization and Physically-Based Rendering"

MeshGPT: Generating Triangle Meshes with Decoder-Only Transformers

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

FlashTex: Fast Relightable Mesh Texturing with LightControlNet

Official Code Release for [SIGGRAPH 2024] DiLightNet: Fine-grained Lighting Control for Diffusion-based Image Generation

Official Implementation for "ConceptLab: Creative Generation using Diffusion Prior Constraints"

Source code for the SIGGRAPH 2024 paper "X-Portrait: Expressive Portrait Animation with Hierarchical Motion Attention"

Official implementation for the paper "VOODOO 3D: Volumetric Portrait Disentanglement for One-Shot 3D Head Reenactment"

Official repo for PhysAvatar: Learning the Physics of Dressed 3D Avatars from Visual Observations, ECCV 2024

[CVPR2024] OHTA: One-shot Hand Avatar via Data-driven Implicit Priors

MultiPly: Reconstruction of Multiple People from Monocular Video in the Wild (CVPR2024 Oral)

[CVPR 2024 Highlight]

Code of MonoHair: High-Fidelity Hair Modeling from a Monocular Video

[Siggraph Asia 2024] Follow-Your-Emoji: This repo is the official implementation of "Follow-Your-Emoji: Fine-Controllable and Expressive Freestyle Portrait Animation"

Real3D-Portrait: One-shot Realistic 3D Talking Portrait Synthesis; ICLR 2024 Spotlight; Official code

Official implementation of EMOPortraits: Emotion-enhanced Multimodal One-shot Head Avatars

Official repo for paper "Structured 3D Latents for Scalable and Versatile 3D Generation".

Official repo for paper "Structured 3D Latents for Scalable and Versatile 3D Generation".

[NeurIPS 2024] HDR 3D Scene Editing!

Official repo for paper "Structured 3D Latents for Scalable and Versatile 3D Generation".

STAR: Spatial-Temporal Augmentation with Text-to-Video Models for Real-World Video Super-Resolution

A ComfyUI custom node implementation for optimized video generation and motion effects, designed to work with Hunyuan text-to-video models.

SPAR3D: Stable Point-Aware Reconstruction of 3D Objects from Single Images