tra2020

SMR

Self-Supervised 3D Mesh Reconstruction from Single Images (CVPR2021)

Fully_3D_Object

GANSVR

SoftRas

Project page of paper "Soft Rasterizer: A Differentiable Renderer for Image-based 3D Reasoning"

Pix2Vox

The official implementation of "Pix2Vox: Context-aware 3D Reconstruction from Single and Multi-view Images". (Xie et al., ICCV 2019)

DirectionNet

Wide-Baseline Relative Camera Pose Estimation with Directional Learning (CVPR 2021)

AttSets

🔥AttSets in Tensorflow (IJCV 2019)

NeuralRecon-W

Code for "Neural 3D Reconstruction in the Wild", SIGGRAPH 2022 (Conference Proceedings)

SkeletonNet

Code and datasets for TPAMI 2021 "SkeletonNet: A Topology-Preserving Solution for Learning Mesh Reconstruction of Object Surfaces from RGB Images "

DISN

DISN: Deep Implicit Surface Network for High-quality Single-view 3D Reconstruction

google-research

Google Research

pix3d

Pix3D: Dataset and Methods for Single-Image 3D Shape Modeling

marrnet

MarrNet: 3D Shape Reconstruction via 2.5D Sketches

dex-nerf-datasets

Datasets for Dex-NeRF: Using a Neural Radiance field to Grasp Transparent Objects

TranspareNet

Seeing Glass: Joint Point-Cloud and Depth Completion for Transparent Objects. CoRL 2021

IM-NET-pytorch

PyTorch 1.2 implementation of IM-NET.

implicit_depth

RGB-D Local Implicit Function for Depth Completion of Transparent Objects

occupancy_networks

This repository contains the code for the paper "Occupancy Networks - Learning 3D Reconstruction in Function Space"

3D-R2N2

Single/multi view image(s) to voxel reconstruction using a recurrent neural network

AtlasNet

This repository contains the source codes for the paper "AtlasNet: A Papier-Mâché Approach to Learning 3D Surface Generation ". The network is able to synthesize a mesh (point cloud + connectivity) from a low-resolution point cloud, or from an image.

implicit-decoder

The code for paper "Learning Implicit Fields for Generative Shape Modeling".

TransCG

[RAL 2022 & ICRA 2023] TransCG: A Large-Scale Real-World Dataset for Transparent Object Depth Completion and A Grasping Baseline

Pixel2Mesh

Pixel2Mesh: Generating 3D Mesh Models from Single RGB Images. In ECCV2018.

Pixel2MeshPlusPlus

Pixel2Mesh++: Multi-View 3D Mesh Generation via Deformation. In ICCV2019.

Front2Back

Official implementation of CVPR 2020 paper "Front2Back: Single View 3D Shape Reconstruction via Front to Back Prediction"

idr

differentiable-point-clouds

The reference implementation of "Unsupervised Learning of Shape and Pose with Differentiable Point Clouds"

mvcSnP

Code release for "Multi-view Consistency as Supervisory Signal for Learning Shape and Pose Prediction"

2D_projection_matching

DRT

SIGGRAPH Asia 2020: Differentiable Refraction-Tracing for Mesh Reconstruction of Transparent Objects