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

[CVPR 2024 Oral] Rethinking Inductive Biases for Surface Normal Estimation

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

A list of Human-Object Interaction Learning.

More relighting!

Implementation of the SIGGRAPH 2024 conference paper "High-quality Surface Reconstruction using Gaussian Surfels".

Official repository for CVPR 2024 highlight paper 4D-DRESS: A 4D Dataset of Real-world Human Clothing with Semantic Annotations.

[CVPR 2024] SiTH: Single-view Textured Human Reconstruction with Image-Conditioned Diffusion

[ECCV 2024] RGBD GS-ICP SLAM

[CVPR'24 Highlight & Best Demo Award] Gaussian Splatting SLAM

[ECCV'24] GeoWizard: Unleashing the Diffusion Priors for 3D Geometry Estimation from a Single Image

DUSt3R: Geometric 3D Vision Made Easy

[CVPR 2024] Depth Anything: Unleashing the Power of Large-Scale Unlabeled Data. Foundation Model for Monocular Depth Estimation

[CVPR'24] Group Anything with Radiance Fields

[ECCV'2024] Gaussian Grouping for open-world Anything reconstruction, segmentation and editing.

An open-source impl. of Large Reconstruction Models

[CVPR 2024] Official PyTorch implementation of SuGaR: Surface-Aligned Gaussian Splatting for Efficient 3D Mesh Reconstruction and High-Quality Mesh Rendering

HOSNeRF: Dynamic Human-Object-Scene Neural Radiance Fields from a Single Video

[CVPR 2024✨Highlight] Official repository for HOLD, the first method that jointly reconstructs articulated hands and objects from monocular videos without assuming a pre-scanned object template and…

Curated list of papers and resources focused on 3D Gaussian Splatting, intended to keep pace with the anticipated surge of research in the coming months.

[CVPR 2024 Highlight] PhysGaussian: Physics-Integrated 3D Gaussians for Generative Dynamics

This repository contains a pytorch implementation of "SelfRecon: Self Reconstruction Your Digital Avatar from Monocular Video (CVPR 2022, Oral)".

[ICCV 2023] Total-Recon: Deformable Scene Reconstruction for Embodied View Synthesis

Training library for local feature detection and matching

[ICLR 2024 Oral] Generative Gaussian Splatting for Efficient 3D Content Creation

Waymo Open Dataset

Doppelgangers: Learning to Disambiguate Images of Similar Structures

A unified framework for 3D content generation.

code release of paper "DIMOS: Synthesizing Diverse Human Motions in 3D Indoor Scenes"