Learning View Priors for Single-view 3D Reconstruction (CVPR 2019)

Last update: Aug 17, 2022

Related tags

Deep Learning view_prior_learning

Overview

Learning View Priors for Single-view 3D Reconstruction (CVPR 2019)

This is code for a paper Learning View Priors for Single-view 3D Reconstruction by Hiroharu Kato and Tatsuya Harada.

For more details, please visit project page.

Environment

This code is tested on Python 2.7.

Testing pretrained models

Download datasets and pretrained models from here and extract them under data directory. This can be done by the following commands.

mkdir data
cd data
wget --load-cookies /tmp/cookies.txt "https://docs.google.com/uc?export=download&confirm=$(wget --quiet --save-cookies /tmp/cookies.txt --keep-session-cookies --no-check-certificate 'https://docs.google.com/uc?export=download&id=1G5gelwQGniwGgyG92ls_dfc1VtLUiM3s' -O- | sed -rn 's/.*confirm=([0-9A-Za-z_]+).*/\1\n/p')&id=1G5gelwQGniwGgyG92ls_dfc1VtLUiM3s" -O dataset.zip && rm -rf /tmp/cookies.txt
wget --load-cookies /tmp/cookies.txt "https://docs.google.com/uc?export=download&confirm=$(wget --quiet --save-cookies /tmp/cookies.txt --keep-session-cookies --no-check-certificate 'https://docs.google.com/uc?export=download&id=119D78nZ329J90yTkfSrq4imRuQ8ON5N_' -O- | sed -rn 's/.*confirm=([0-9A-Za-z_]+).*/\1\n/p')&id=119D78nZ329J90yTkfSrq4imRuQ8ON5N_" -O models.zip && rm -rf /tmp/cookies.txt
unzip dataset.zip
unzip models.zip
cd ../

Quantitative evaluation of our best model on ShapeNet dataset is done by the following command.

python ./mesh_reconstruction/test.py -ds shapenet -nt 0 -eid shapenet_multi_color_nv20_uvr_cc_long

This outputs

02691156 0.691549002544
02828884 0.59788288686
02933112 0.720973934558
02958343 0.804359183654
03001627 0.603543199669
03211117 0.593105481352
03636649 0.502730883482
03691459 0.673864365473
04090263 0.664089877796
04256520 0.654773500288
04379243 0.602735843742
04401088 0.767574659204
04530566 0.616663414002
all 0.653372787125

Other ShapeNet models are listed in test_shapenet.sh.

Drawing animated gif of ShapeNet reconstruction requires the dataset provided by [Kar et al. NIPS 2017].

cd data
wget --load-cookies /tmp/cookies.txt "https://docs.google.com/uc?export=download&confirm=$(wget --quiet --save-cookies /tmp/cookies.txt --keep-session-cookies --no-check-certificate 'https://docs.google.com/uc?export=download&id=17GjULuQZsn-s92PQFQSBzezDkonowIxR' -O- | sed -rn 's/.*confirm=([0-9A-Za-z_]+).*/\1\n/p')&id=17GjULuQZsn-s92PQFQSBzezDkonowIxR" -O lsm.tar.gz && rm -rf /tmp/cookies.txt
tar xvzf lsm.tar.gz
cd shapenet_release/renders/
find ./ -name "*.tar.gz" -exec tar xvzf {} \;
cd ../../../

Then, the following commands

mkdir tmp
bash make_gif.sh

output the following images.

Training

Training requires pre-trained AlexNet model.

cd data
mkdir caffemodel
cd caffemodel
wget http://dl.caffe.berkeleyvision.org/bvlc_alexnet.caffemodel
cd ../../

Training of the provided pre-trained models is done by

bash train_shapenet.sh
bash train_pascal.sh

Citation

@InProceedings{kato2019vpl,
    title={Learning View Priors for Single-view 3D Reconstruction},
    author={Hiroharu Kato and Tatsuya Harada},
    booktitle={The IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
    year={2019}
}

Learning View Priors for Single-view 3D Reconstruction (CVPR 2019)

Related tags

Overview

Learning View Priors for Single-view 3D Reconstruction (CVPR 2019)

Environment

Testing pretrained models

Training

Citation

Owner

Hiroharu Kato

'Aligned mixture of latent dynamical systems' (amLDS) for stimulus decoding probabilistic manifold alignment across animals. P. Herrero-Vidal et al. NeurIPS 2021 code.

WRENCH: Weak supeRvision bENCHmark

A PaddlePaddle implementation of STGCN with a few modifications in the model architecture in order to forecast traffic jam.

Generating Images with Recurrent Adversarial Networks

Reproducible research and reusable acyclic workflows in Python. Execute code on HPC systems as if you executed them on your personal computer!

DeLiGAN - This project is an implementation of the Generative Adversarial Network

Implementation of Learning Gradient Fields for Molecular Conformation Generation (ICML 2021).

HCQ: Hybrid Contrastive Quantization for Efficient Cross-View Video Retrieval

Contains code for the paper "Vision Transformers are Robust Learners".

Code for SentiBERT: A Transferable Transformer-Based Architecture for Compositional Sentiment Semantics (ACL'2020).

AIR^2 for Interaction Prediction

Chinese named entity recognization with BiLSTM using Keras

Keras implementation of AdaBound

Neurolab is a simple and powerful Neural Network Library for Python

Revitalizing CNN Attention via Transformers in Self-Supervised Visual Representation Learning

Contrastive Learning with Non-Semantic Negatives

[CVPR 2022] Back To Reality: Weak-supervised 3D Object Detection with Shape-guided Label Enhancement

A Pytorch implementation of MoveNet from Google. Include training code and pre-train model.

Spectral normalization (SN) is a widely-used technique for improving the stability and sample quality of Generative Adversarial Networks (GANs)

[NeurIPS 2021] Large Scale Learning on Non-Homophilous Graphs: New Benchmarks and Strong Simple Methods