The open-source tool for building high-quality datasets and computer vision models

HOT3D: A dataset for egocentric 3D hand and object tracking

Self-ShadowGAN

TetSphere Splatting: Representing High-Quality Geometry with Lagrangian Volumetric Meshes

Implementation of the paper "3D Gaussian Splatting as Markov Chain Monte Carlo"

Our CVPR 2024 paper 'Bayesian Differentiable Physics for Cloth Digitalization'

Code for Carve3D: Improving Multi-view Reconstruction Consistency for Diffusion Models with RL Finetuning

Source code for the SIGGRAPH 2024 conference paper "Neural Geometry Fields for Meshes"

[SIGGRAPH'24] A Construct-Optimize Approach to Sparse View Synthesis without Camera Pose

[CVPR 2024] The dataset, code, and model for our paper "Shadow Generation for Composite Image Using Diffusion Model", CVPR, 2024.

Official code for arxiv paper LRM-Zero: Training Large Reconstruction Models with Synthesized Data

Our CVPR 2024 paper 'Human Motion Prediction under Unexpected Perturbation'

Implementation of SIGGRAPH 2022 paper "Computational Design of High-level Interlocking Puzzles"

[SIGGRAPH'24] Code Release for "Bilateral Guided Radiance Field Processing"

The official implementation of "CityDreamer: Compositional Generative Model of Unbounded 3D Cities". (Xie et al., CVPR 2024)

[CVPR2024] DPHMs: Diffusion Parametric Head Models for Depth-based Tracking

[CVPR24] MaGGIe: Mask Guided Gradual Human Instance Matting

Code release for "Terrain Amplification using Multi-scale Erosion"

STaRK: Benchmarking LLM Retrieval on Textual and Relational Knowledge Bases

[CVPR 2024] Official repo for "InteractDiffusion: Interaction-Control for Text-to-Image Diffusion Model".

Looking 3D: Anomaly Detection with 2D-3D Alignment (CVPR24)

PyTorch implementation for the paper Don't Look into the Dark: Latent Codes for Pluralistic Image Inpainting (CVPR2024).

HAAR: Text-Conditioned Generative Model of 3D Strand-based Human Hairstyles (CVPR 2024)

Video Generation, Physical Commonsense, Semantic Adherence, VideoCon-Physics

[CVPR2024] VideoBooth: Diffusion-based Video Generation with Image Prompts

This is the code repository for the paper: Hand-Object Interaction Controller (HOIC): Deep Reinforcement Learning for Reconstructing Interactions with Physics

[SIGGRAPH'24] 2D Gaussian Splatting for Geometrically Accurate Radiance Fields