chuanfushen

tsdf-fusion

Fuse multiple depth frames into a TSDF voxel volume.

LaRa

[ECCV 2024] Efficient Large-Baseline Radiance Fields, a feed-forward 2DGS model

3D_Data_Acquisition_Registration_Using_Kinects

3D data acquisition and registration using two opposing Kinects.

Point-SLAM

Point-SLAM: Dense Neural Point Cloud-based SLAM

LiveScan3D

LiveScan3D is a system designed for real time 3D reconstruction using multiple Azure Kinect or Kinect v2 depth sensors simultaneously at real time speed.

KinectFusion

Implementation of the KinectFusion approach by python

KinectFusion

KinectFusion implemented in Python with PyTorch

Passersby-Anonymizer

LangSplat

Official implementation of the paper "LangSplat: 3D Language Gaussian Splatting" [CVPR2024 Highlight]

if-net

Implicit Feature Network (IF-Net) - Codebase

ViewDiff

ViewDiff generates high-quality, multi-view consistent images of a real-world 3D object in authentic surroundings. (CVPR2024).

npms

Official implementation of NPMs: Neural Parametric Models for 3D Deformable Shapes - ICCV 2021

NeuralGraph

Official implementation for CVPR'2021 paper Neural Deformation Graphs

opencv_contrib

Repository for OpenCV's extra modules

SeSDF

SeSDF: Self-evolved Signed Distance Field for Implicit 3D Clothed Human Reconstruction

3dHumanBodyReconstruction

3D human body reconstruction based on kinect v1

CONTHO_RELEASE

[CVPR 2024] This repo is official PyTorch implementation of Joint Reconstruction of 3D Human and Object via Contact-Based Refinement Transformer.

oplanes

[AAAI 2023] Official implementation of "Occupancy Planes for Single-view RGB-D Human Reconstruction"

Detailed-VideoAvatar

Reproduced Detailed-VideoAvatar project for 3D Human-Body Reconstruction

Detailed-VideoAvatar

Reproduced Detailed-VideoAvatar project for 3D Human-Body Reconstruction

3D-Human-Body-Surface-Reconstruction-System

User interface for 3D human body surface reconstruction system. Taking depth stream as input, generate 3D partial meshes for poses.

meshavatar

Code Repository for MeshAvatar: Learning High-quality Triangular Human Avatars from Multi-view Videos (ECCV 2024)

4d-gaussian-splatting

[ICLR 2024] Real-time Photorealistic Dynamic Scene Representation and Rendering with 4D Gaussian Splatting

colmap

COLMAP - Structure-from-Motion and Multi-View Stereo

Semantify

STRAPS-3DHumanShapePose

Code repository for the paper: Synthetic Training for Accurate 3D Human Pose and Shape Estimation in the Wild (BMVC 2020)

SMPL-Anthropometry

Measure the SMPL body model

DrivingGaussian

[CVPR 2024] DrivingGaussian: Composite Gaussian Splatting for Surrounding Dynamic Autonomous Driving Scenes

torchsparse

[MICRO'23, MLSys'22] TorchSparse: Efficient Training and Inference Framework for Sparse Convolution on GPUs.

ALSO

ALSO: Automotive Lidar Self-supervision by Occupancy estimation