All Projects → shubhtuls → Mvcsnp

shubhtuls / Mvcsnp

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

Programming Languages

lua
6591 projects

Projects that are alternatives of or similar to Mvcsnp

Pifu
This repository contains the code for the paper "PIFu: Pixel-Aligned Implicit Function for High-Resolution Clothed Human Digitization"
Stars: ✭ 1,021 (+803.54%)
Mutual labels:  3d-reconstruction
Bundler sfm
Bundler Structure from Motion Toolkit
Stars: ✭ 1,296 (+1046.9%)
Mutual labels:  3d-reconstruction
Awsome deep geometry learning
A list of resources about deep learning solutions on 3D shape processing
Stars: ✭ 105 (-7.08%)
Mutual labels:  3d-reconstruction
Vgg Multiple View Geometry
A set of MATLAB utilities for multiple view geometry, provided alongside Hartley & Zisserman's "Multiple View Geometry in Computer Vision, Second Edition" (2004). Obtained from http://www.robots.ox.ac.uk/~vgg/hzbook/code/.
Stars: ✭ 62 (-45.13%)
Mutual labels:  3d-reconstruction
Pymeshfix
Python Wrapper for MeshFix: easily repair holes in PyVista surface meshes
Stars: ✭ 75 (-33.63%)
Mutual labels:  3d-reconstruction
Pix2face
3D human face estimation and rendering from a single image
Stars: ✭ 89 (-21.24%)
Mutual labels:  3d-reconstruction
Bundlefusion
[Siggraph 2017] BundleFusion: Real-time Globally Consistent 3D Reconstruction using Online Surface Re-integration
Stars: ✭ 979 (+766.37%)
Mutual labels:  3d-reconstruction
Sgnn
[CVPR'20] SG-NN: Sparse Generative Neural Networks for Self-Supervised Scene Completion of RGB-D Scans
Stars: ✭ 112 (-0.88%)
Mutual labels:  3d-reconstruction
Dj Rn
As a part of HAKE project (HAKE-3D). Code for our CVPR2020 paper "Detailed 2D-3D Joint Representation for Human-Object Interaction".
Stars: ✭ 78 (-30.97%)
Mutual labels:  3d-reconstruction
Planematch
[ECCV'18 Oral] PlaneMatch: Patch Coplanarity Prediction for Robust RGB-D Reconstruction
Stars: ✭ 105 (-7.08%)
Mutual labels:  3d-reconstruction
Py3drec
3D modeling from uncalibrated images
Stars: ✭ 65 (-42.48%)
Mutual labels:  3d-reconstruction
3d Reconstruction With Neural Networks
3D reconstruction with neural networks using Tensorflow. See link for Video (https://www.youtube.com/watch?v=iI6ZMST8Ri0)
Stars: ✭ 71 (-37.17%)
Mutual labels:  3d-reconstruction
3d Recgan Extended
🔥3D-RecGAN++ in Tensorflow (TPAMI 2018)
Stars: ✭ 98 (-13.27%)
Mutual labels:  3d-reconstruction
Floor Sp
Floor-SP: Inverse CAD for Floorplans by Sequential Room-wise Shortest Path, ICCV 2019
Stars: ✭ 54 (-52.21%)
Mutual labels:  3d-reconstruction
Pcl Learning
🔥PCL(Point Cloud Library)点云库学习记录
Stars: ✭ 106 (-6.19%)
Mutual labels:  3d-reconstruction
Mirror
Matchable Image Retrieval by Learning from Surface Reconstruction
Stars: ✭ 44 (-61.06%)
Mutual labels:  3d-reconstruction
Igr
Implicit Geometric Regularization for Learning Shapes
Stars: ✭ 90 (-20.35%)
Mutual labels:  3d-reconstruction
Sobfu
real-time 3D reconstruction of non-rigidly deforming scenes using depth data
Stars: ✭ 113 (+0%)
Mutual labels:  3d-reconstruction
Unsupervised Depth Completion Visual Inertial Odometry
Tensorflow implementation of Unsupervised Depth Completion from Visual Inertial Odometry (in RA-L January 2020 & ICRA 2020)
Stars: ✭ 109 (-3.54%)
Mutual labels:  3d-reconstruction
Objectron
Objectron is a dataset of short, object-centric video clips. In addition, the videos also contain AR session metadata including camera poses, sparse point-clouds and planes. In each video, the camera moves around and above the object and captures it from different views. Each object is annotated with a 3D bounding box. The 3D bounding box describes the object’s position, orientation, and dimensions. The dataset contains about 15K annotated video clips and 4M annotated images in the following categories: bikes, books, bottles, cameras, cereal boxes, chairs, cups, laptops, and shoes
Stars: ✭ 1,352 (+1096.46%)
Mutual labels:  3d-reconstruction

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

Shubham Tulsiani, Alexei A. Efros, Jitendra Malik.

Project Page

Installation

First, you'll need a working implementation of Torch. The subsequent installation steps are:

##### Install 3D spatial transformer ######
cd external/stn3d
luarocks make stn3d-scm-1.rockspec

##### Additional Dependencies (json and matio) #####
sudo apt-get install libmatio2
luarocks install matio
luarocks install json

Training and Evaluating

To train or evaluate the (trained/downloaded) models, it is first required to download the Shapenet dataset (v1) and preprocess the data to compute renderings and voxelizations. Please see the detailed README files for Training or Evaluation of models for subsequent instructions.

Demo and Pre-trained Models

Please check out the interactive notebook which shows reconstructions using the learned models. You'll need to -

  • Install a working implementation of torch and itorch.
  • Download the pre-trained models (1.5GB) and extract them to 'cachedir/snapshots/shapenet/'
  • Edit the absolute paths to the blender executable and the provided '.blend' file in the rendering utility script.

Citation

If you use this code for your research, please consider citing:

@inProceedings{mvcTulsiani18,
  title={Multi-view Consistency as Supervisory Signal
  for Learning Shape and Pose Prediction},
  author = {Shubham Tulsiani
  and Alexei A. Efros
  and Jitendra Malik},
  booktitle={Computer Vision and Pattern Regognition (CVPR)},
  year={2018}
}
Note that the project description data, including the texts, logos, images, and/or trademarks, for each open source project belongs to its rightful owner. If you wish to add or remove any projects, please contact us at [email protected].