Open-source alternatives to SSR Code

This is the reference implementation of "Learning Generative Models of Textured 3D Meshes from Real-World Images", accepted at ICCV 2021.

Srinath Sridhar 1 , Davis Rempe 1 , Julien Valentin 2 , Sofien Bouaziz 2 , Leonidas J. Guibas 1,3 1 Stanford University , 2 Google Inc. , 3 Facebook AI Research

This is the source code of Self-Supervised 3D Mesh Reconstruction From Single Images (CVPR-2021).

Neural Template: Topology-aware Reconstruction and Disentangled Generation of 3D Meshes (CVPR 2022)

Training scripts and a couple of trained demo networks are included. More demos and the complete set of data are on the road.

Official implementation for the paper

TBD

Pytorch Implementation of https://arxiv.org/abs/1812.01742

This is not an officially supported Google product.

OctNet uses efficient space partitioning structures (i.e. octrees) to reduce memory and compute requirements of 3D convolutional neural networks, thereby enabling deep learning at high resolutions.

This repository is the implementation of our AAAI 2019 paper:

This repository contains the source code for the paper Pix2Vox: Context-aware 3D Reconstruction from Single and Multi-view Images. The follow-up work Pix2Vox++: Multi-scale Context-aware 3D Object Reconstruction from Single and Multiple Images has been published in International Journal of…

This is an official PyTorch implementation of the E 2 NeRF. Click here to see the video and supplementary materials in our project website.

Here you'll find the codes for the paper Image2Mesh: A Learning Framework for Single Image 3D Reconstruction.

This repository contains the source codes for the paper Deep Mesh Reconstruction from Single RGB Images via Topology Modification Networks.

This repository contains the code for the paper. 3D Shape Reconstruction from 2D Images with Disentangled Attribute Flow.

This project is a work in progress.

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

Evaluation and visualization code accompanying the CVPR'19 paper "What Do Single-view 3D Reconstruction Networks Learn?" by M. Tatarchenko, S. R. Richter, R. Ranftl, Z. Li, V. Koltun, and T. Brox (*indicates equal contribution).

Our training data includes the images, normal maps and the 3D supervision, all downloaded from datasets provided by DISN. Please download the dataset into folder ./data/.

Dependencies

Official PyTorch implementation of Height and Uprightness Invariance for 3D Prediction from a Single View (CVPR 2020)

This repository contains the TensorFlow implementation for the following paper