Official repository of In-Context LoRA for Diffusion Transformers

No Pose, No Problem: Surprisingly Simple 3D Gaussian Splats from Sparse Unposed Images

[NeuRIPS, 2024] Multi-Human Dataset for Close Interactions.

Code for Paper: Learning Implicit Representation for Reconstructing Articulated Objects

[SIGGRAPH Asia 2024] PuzzleAvatar: Assembling 3D Avatars from Personal Albums

Goliath Dataset and Official PyTorch Implementation of RelightableHands, Relightable Gaussian Codec Avatars, and Driving-Signal Aware Full-Body Avatars.

Train universal codec avatars

MotionBank: A Large-scale Video Motion Benchmark with Disentangled Rule-based Annotations

Official repository for paper "MagicMan: Generative Novel View Synthesis of Humans with 3D-Aware Diffusion and Iterative Refinement"

Efficient vision foundation models for high-resolution generation and perception.

Official implementation of MagicClay: Sculpting Meshes with Generative Neural Fields (Siggraph Asia 2024)

PyTorch Extension Library of Optimized Autograd Sparse Matrix Operations

Meta Lingua: a lean, efficient, and easy-to-hack codebase to research LLMs.

MoVQGAN - model for the image encoding and reconstruction

DUSt3R: Geometric 3D Vision Made Easy

Bag of Tricks and A Strong Baseline for Deep Person Re-identification

Official implementation for "CLIP-ReID: Exploiting Vision-Language Model for Image Re-identification without Concrete Text Labels" (AAAI 2023)

田柯宇 (Tian Keyu)恶意攻击集群事件的证据揭露

[NeurIPS 2024] MotionGS: Exploring Explicit Motion Guidance for Deformable 3D Gaussian Splatting

Movie Gen Bench - two media generation evaluation benchmarks released with Meta Movie Gen

Simple project page template for your research paper, built with Astro and Tailwind CSS

GeoMaster: Advanced Geometry Enhancement for High-Resolution 3D Modeling

Diffusion base mining

Awesome Person Re-identification

[NeurIPS 2024] "DreamMesh4D: Video-to-4D Generation with Sparse-Controlled Gaussian-Mesh Hybrid Representation"