MVPaint: Synchronized Multi-View Diffusion for Painting Anything 3D

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

FasterCache: Training-Free Video Diffusion Model Acceleration with High Quality

DynamicCity: Large-Scale LiDAR Generation from Dynamic Scenes

[arXiv'24] VistaDream: Sampling multiview consistent images for single-view scene reconstruction

MMHead: Towards Fine-grained Multi-modal 3D Facial Animation (ACM MM 2024)

[arXiv 2024] GS-VTON: Controllable 3D Virtual Try-on with Gaussian Splatting

Omni6D: Large-Vocabulary 3D Object Dataset for Category-Level 6D Object Pose Estimation

MLLM for On-Demand Spatial-Temporal Understanding at Arbitrary Resolution

Toolbox for GTA-Human Datasets

3DTopia-XL: High-Quality 3D PBR Asset Generation via Primitive Diffusion

Phidias: A Generative Model for Creating 3D Content from Text, Image, and 3D Conditions with Reference-Augmented Diffusion

A light-weight and high-efficient training framework for accelerating diffusion tasks.

Vchitect-2.0: Parallel Transformer for Scaling Up Video Diffusion Models

Official code of "LayerPano3D: Layered 3D Panorama for Hyper-Immersive Scene Generation"

Generalized Out-of-Distribution Detection and Beyond in Vision Language Model Era: A Survey [Miyai+, arXiv2024]

Official Code for "Digital Life Project: Autonomous 3D Characters with Social Intelligence"

[ECCV 2024] 4D Contrastive Superflows are Dense 3D Representation Learners

[ArXiv 2024] WildAvatar: Web-scale In-the-wild Video Dataset for 3D Avatar Creation

Official codes of VEnhancer: Generative Space-Time Enhancement for Video Generation

Code for FreeTraj, a tuning-free method for trajectory-controllable video generation

Long Context Transfer from Language to Vision

The official implementation of "GaussianCity: Generative Gaussian Splatting for Unbounded 3D City Generation". (Xie et al., arXiv 2406.06526)

[ECCV 2024] MVSGaussian: Fast Generalizable Gaussian Splatting Reconstruction from Multi-View Stereo

4D Panoptic Scene Graph Generation (NeurIPS'23 Spotlight)