Stars
DeepVerse: 4D Autoregressive Video Generation as a World Model
OmniVCus: Feedforward Subject-driven Video Customization with Multimodal Control Conditions
Streaming 3D Reconstruction with Explicit Spatial Pointer Memory
Official code repository for FlashDepth: Real-time Streaming Video Depth Estimation at 2K Resolution
Official inference repo for FLUX.1 models
OmniGen2: Exploration to Advanced Multimodal Generation.
[CVPR 2025] Towards In-the-wild 3D Plane Reconstruction from a Single Image
Official repo for paper "Sparse Representation and Construction for High-Resolution 3D Shapes Modeling".
From Images to High-Fidelity 3D Assets with Production-Ready PBR Material
[ICCV 2025] Official code for AnimateAnyMesh: A Feed-Forward 4D Foundation Model for Text-Driven Universal Mesh Animation
PyTorch code and models for VJEPA2 self-supervised learning from video.
Efficient Part-level 3D Object Generation via Dual Volume Packing
AllTracker is a model for tracking all pixels in a video.
PartCrafter: Structured 3D Mesh Generation via Compositional Latent Diffusion Transformers
[ICCV 2025] SpatialTrackerV2: 3D Point Tracking Made Easy
Public code release associated with SceneScript.
SpatialLM: Training Large Language Models for Structured Indoor Modeling
Generative Omnimatte (CVPR 2025)
🤗 PEFT: State-of-the-art Parameter-Efficient Fine-Tuning.
Uni3C: Unifying Precisely 3D-Enhanced Camera and Human Motion Controls for Video Generation
A Native Multimodal LLM for 3D Generation and Understanding
AnyCalib: On-Manifold Learning for Model-Agnostic Single-View Camera Calibration (ICCV 2025)
Official implementation of "UniTEX: Universal High Fidelity Generative Texturing for 3D Shapes"
Official code for the CVPR 2025 paper "Navigation World Models".
Official implementation of EPiC: Efficient Video Camera Control Learning with Precise Anchor-Video Guidance