GeneGAN: Learning Object Transfiguration and Attribute Subspace from Unpaired Data

Overview

GeneGAN: Learning Object Transfiguration and Attribute Subspace from Unpaired Data

By Shuchang Zhou, Taihong Xiao, Yi Yang, Dieqiao Feng, Qinyao He, Weiran He

If you use this code for your research, please cite our paper:

@inproceedings{DBLP:conf/bmvc/ZhouXYFHH17,
  author    = {Shuchang Zhou and
               Taihong Xiao and
               Yi Yang and
               Dieqiao Feng and
               Qinyao He and
               Weiran He},
  title     = {GeneGAN: Learning Object Transfiguration and Attribute Subspace from Unpaired Data},
  booktitle = {Proceedings of the British Machine Vision Conference (BMVC)},
  year      = {2017},
  url       = {http://arxiv.org/abs/1705.04932},
  timestamp = {http://dblp.uni-trier.de/rec/bib/journals/corr/ZhouXYFHH17},
  bibsource = {dblp computer science bibliography, http://dblp.org}
}

We have two following papers, DNA-GAN and ELEGANT, that generalize the method into multiple attributes case. It is worth mentioning that ELEGANT can transfer multiple face attributes on high resolution images. Please pay attention to our new methods!

Introduction

This is the official source code for the paper GeneGAN: Learning Object Transfiguration and Attribute Subspace from Unpaired Data. All the experiments are initially done in our proprietary deep learning framework. For convenience, we reproduce the results using TensorFlow.

cross

GeneGAN is a deterministic conditional generative model that can learn to disentangle the object features from other factors in feature space from weak supervised 0/1 labeling of training data. It allows fine-grained control of generated images on one certain attribute in a continous way.

Requirement

  • Python 3.5
  • TensorFlow 1.0
  • Opencv 3.2

Training GeneGAN on celebA dataset

  1. Download celebA dataset and unzip it into datasets directory. There are various source providers for CelebA datasets. To ensure that the size of downloaded images is correct, please run identify datasets/celebA/data/000001.jpg. The size should be 409 x 687 if you are using the same dataset. Besides, please ensure that you have the following directory tree structure.
├── datasets
│   └── celebA
│       ├── data
│       ├── list_attr_celeba.txt
│       └── list_landmarks_celeba.txt
  1. Run python preprocess.py. It will take several miniutes to preprocess all face images. A new directory datasets/celebA/align_5p will be created.

  2. Run python train.py -a Bangs -g 0 to train GeneGAN on the attribute Bangs. You can train GeneGAN on other attributes as well. All available attribute names are listed in the list_attr_celeba.txt file.

  3. Run tensorboard --logdir='./' --port 6006 to watch your training process.

Testing

We provide three kinds of mode for test. Run python test.py -h for detailed help. The following example is running on our GeneGAN model trained on the attribute Bangs. Have fun!

1. Swapping of Attributes

You can easily add the bangs of one person to another person without bangs by running

python test.py -m swap -i datasets/celebA/align_5p/182929.jpg -t datasets/celebA/align_5p/022344.jpg
input target out1 out2
Swap Attribute

2. Linear Interpolation of Image Attributes

Besides, we can control to which extent the bangs style is added to your input image through linear interpolation of image attribute. Run the following code.

python test.py -m interpolation -i datasets/celebA/align_5p/182929.jpg -t datasets/celebA/align_5p/035460.jpg -n 5
interpolation target
Linear Interpolation

3. Matrix Interpolation in Attribute Subspace

We can do something cooler. Given four images with bangs attributes at hand, we can observe the gradual change process of our input images with a mixing of difference bangs style.

python test.py -m matrix -i datasets/celebA/align_5p/182929.jpg --targets datasets/celebA/align_5p/035460.jpg datasets/celebA/align_5p/035451.jpg datasets/celebA/align_5p/035463.jpg datasets/celebA/align_5p/035474.jpg -s 5 5
matrix
Matrix Interpolation

Single-Stage 6D Object Pose Estimation, CVPR 2020

Overview This repository contains the code for the paper Single-Stage 6D Object Pose Estimation. Yinlin Hu, Pascal Fua, Wei Wang and Mathieu Salzmann.

CVLAB @ EPFL 89 Dec 26, 2022
Luminous is a framework for testing the performance of Embodied AI (EAI) models in indoor tasks.

Luminous is a framework for testing the performance of Embodied AI (EAI) models in indoor tasks. Generally, we intergrete different kind of functional

28 Jan 08, 2023
Modified fork of Xuebin Qin's U-2-Net Repository. Used for demonstration purposes.

U^2-Net (U square net) Modified version of U2Net used for demonstation purposes. Paper: U^2-Net: Going Deeper with Nested U-Structure for Salient Obje

Shreyas Bhat Kera 13 Aug 28, 2022
Official Implementation for HyperStyle: StyleGAN Inversion with HyperNetworks for Real Image Editing

HyperStyle: StyleGAN Inversion with HyperNetworks for Real Image Editing Yuval Alaluf*, Omer Tov*, Ron Mokady, Rinon Gal, Amit H. Bermano *Denotes equ

885 Jan 06, 2023
Unofficial PyTorch implementation of Google AI's VoiceFilter system

VoiceFilter Note from Seung-won (2020.10.25) Hi everyone! It's Seung-won from MINDs Lab, Inc. It's been a long time since I've released this open-sour

MINDs Lab 883 Jan 07, 2023
Pytorch implementation of "Neural Wireframe Renderer: Learning Wireframe to Image Translations"

Neural Wireframe Renderer: Learning Wireframe to Image Translations Pytorch implementation of ideas from the paper Neural Wireframe Renderer: Learning

Yuan Xue 7 Nov 14, 2022
Maximum Spatial Perturbation for Image-to-Image Translation (Official Implementation)

MSPC for I2I This repository is by Yanwu Xu and contains the PyTorch source code to reproduce the experiments in our CVPR2022 paper Maximum Spatial Pe

51 Dec 14, 2022
Real-time Neural Representation Fusion for Robust Volumetric Mapping

NeuralBlox: Real-Time Neural Representation Fusion for Robust Volumetric Mapping Paper | Supplementary This repository contains the implementation of

ETHZ ASL 106 Dec 24, 2022
Original code for "Zero-Shot Domain Adaptation with a Physics Prior"

Zero-Shot Domain Adaptation with a Physics Prior [arXiv] [sup. material] - ICCV 2021 Oral paper, by Attila Lengyel, Sourav Garg, Michael Milford and J

Attila Lengyel 40 Dec 21, 2022
g2o: A General Framework for Graph Optimization

g2o - General Graph Optimization Linux: Windows: g2o is an open-source C++ framework for optimizing graph-based nonlinear error functions. g2o has bee

Rainer Kümmerle 2.5k Dec 30, 2022
Code and results accompanying our paper titled Mixture Proportion Estimation and PU Learning: A Modern Approach at Neurips 2021 (Spotlight)

Mixture Proportion Estimation and PU Learning: A Modern Approach This repository is the official implementation of Mixture Proportion Estimation and P

Approximately Correct Machine Intelligence (ACMI) Lab 23 Dec 28, 2022
A small library of 3D related utilities used in my research.

utils3D A small library of 3D related utilities used in my research. Installation Install via GitHub pip install git+https://github.com/Steve-Tod/util

Zhenyu Jiang 8 May 20, 2022
This project provides an unsupervised framework for mining and tagging quality phrases on text corpora with pretrained language models (KDD'21).

UCPhrase: Unsupervised Context-aware Quality Phrase Tagging To appear on KDD'21...[pdf] This project provides an unsupervised framework for mining and

Xiaotao Gu 146 Dec 22, 2022
A curated list of neural rendering resources.

Awesome-of-Neural-Rendering A curated list of neural rendering and related resources. Please feel free to pull requests or open an issue to add papers

Zhiwei ZHANG 43 Dec 09, 2022
PyTorch implementation of DeepLab v2 on COCO-Stuff / PASCAL VOC

DeepLab with PyTorch This is an unofficial PyTorch implementation of DeepLab v2 [1] with a ResNet-101 backbone. COCO-Stuff dataset [2] and PASCAL VOC

Kazuto Nakashima 995 Jan 08, 2023
CTRMs: Learning to Construct Cooperative Timed Roadmaps for Multi-agent Path Planning in Continuous Spaces

CTRMs: Learning to Construct Cooperative Timed Roadmaps for Multi-agent Path Planning in Continuous Spaces This is a repository for the following pape

17 Oct 13, 2022
Classify music genre from a 10 second sound stream using a Neural Network.

MusicGenreClassification Academic research in the field of Deep Learning (Deep Neural Networks) and Sound Processing, Tel Aviv University. Featured in

Matan Lachmish 453 Dec 27, 2022
IJCAI2020 & IJCV 2020 :city_sunrise: Unsupervised Scene Adaptation with Memory Regularization in vivo

Seg_Uncertainty In this repo, we provide the code for the two papers, i.e., MRNet:Unsupervised Scene Adaptation with Memory Regularization in vivo, IJ

Zhedong Zheng 348 Jan 05, 2023
Code for the tech report Toward Training at ImageNet Scale with Differential Privacy

Differentially private Imagenet training Code for the tech report Toward Training at ImageNet Scale with Differential Privacy by Alexey Kurakin, Steve

Google Research 29 Nov 03, 2022
A trusty face recognition research platform developed by Tencent Youtu Lab

Introduction TFace: A trusty face recognition research platform developed by Tencent Youtu Lab. It provides a high-performance distributed training fr

Tencent 956 Jan 01, 2023