This repository contains the code for the paper "PIFu: Pixel-Aligned Implicit Function for High-Resolution Clothed Human Digitization"

Overview

PIFu: Pixel-Aligned Implicit Function for High-Resolution Clothed Human Digitization

report Open In Colab

News:

  • [2020/05/04] Added EGL rendering option for training data generation. Now you can create your own training data with headless machines!
  • [2020/04/13] Demo with Google Colab (incl. visualization) is available. Special thanks to @nanopoteto!!!
  • [2020/02/26] License is updated to MIT license! Enjoy!

This repository contains a pytorch implementation of "PIFu: Pixel-Aligned Implicit Function for High-Resolution Clothed Human Digitization".

Project Page Teaser Image

If you find the code useful in your research, please consider citing the paper.

@InProceedings{saito2019pifu,
author = {Saito, Shunsuke and Huang, Zeng and Natsume, Ryota and Morishima, Shigeo and Kanazawa, Angjoo and Li, Hao},
title = {PIFu: Pixel-Aligned Implicit Function for High-Resolution Clothed Human Digitization},
booktitle = {The IEEE International Conference on Computer Vision (ICCV)},
month = {October},
year = {2019}
}

This codebase provides:

  • test code
  • training code
  • data generation code

Requirements

  • Python 3
  • PyTorch tested on 1.4.0
  • json
  • PIL
  • skimage
  • tqdm
  • numpy
  • cv2

for training and data generation

  • trimesh with pyembree
  • pyexr
  • PyOpenGL
  • freeglut (use sudo apt-get install freeglut3-dev for ubuntu users)
  • (optional) egl related packages for rendering with headless machines. (use apt install libgl1-mesa-dri libegl1-mesa libgbm1 for ubuntu users)

Warning: I found that outdated NVIDIA drivers may cause errors with EGL. If you want to try out the EGL version, please update your NVIDIA driver to the latest!!

Windows demo installation instuction

  • Install miniconda
  • Add conda to PATH
  • Install git bash
  • Launch Git\bin\bash.exe
  • eval "$(conda shell.bash hook)" then conda activate my_env because of this
  • Automatic env create -f environment.yml (look this)
  • OR manually setup environment
    • conda create —name pifu python where pifu is name of your environment
    • conda activate
    • conda install pytorch torchvision cudatoolkit=10.1 -c pytorch
    • conda install pillow
    • conda install scikit-image
    • conda install tqdm
    • conda install -c menpo opencv
  • Download wget.exe
  • Place it into Git\mingw64\bin
  • sh ./scripts/download_trained_model.sh
  • Remove background from your image (this, for example)
  • Create black-white mask .png
  • Replace original from sample_images/
  • Try it out - sh ./scripts/test.sh
  • Download Meshlab because of this
  • Open .obj file in Meshlab

Demo

Warning: The released model is trained with mostly upright standing scans with weak perspectie projection and the pitch angle of 0 degree. Reconstruction quality may degrade for images highly deviated from trainining data.

  1. run the following script to download the pretrained models from the following link and copy them under ./PIFu/checkpoints/.
sh ./scripts/download_trained_model.sh
  1. run the following script. the script creates a textured .obj file under ./PIFu/eval_results/. You may need to use ./apps/crop_img.py to roughly align an input image and the corresponding mask to the training data for better performance. For background removal, you can use any off-the-shelf tools such as removebg.
sh ./scripts/test.sh

Demo on Google Colab

If you do not have a setup to run PIFu, we offer Google Colab version to give it a try, allowing you to run PIFu in the cloud, free of charge. Try our Colab demo using the following notebook: Open In Colab

Data Generation (Linux Only)

While we are unable to release the full training data due to the restriction of commertial scans, we provide rendering code using free models in RenderPeople. This tutorial uses rp_dennis_posed_004 model. Please download the model from this link and unzip the content under a folder named rp_dennis_posed_004_OBJ. The same process can be applied to other RenderPeople data.

Warning: the following code becomes extremely slow without pyembree. Please make sure you install pyembree.

  1. run the following script to compute spherical harmonics coefficients for precomputed radiance transfer (PRT). In a nutshell, PRT is used to account for accurate light transport including ambient occlusion without compromising online rendering time, which significantly improves the photorealism compared with a common sperical harmonics rendering using surface normals. This process has to be done once for each obj file.
python -m apps.prt_util -i {path_to_rp_dennis_posed_004_OBJ}
  1. run the following script. Under the specified data path, the code creates folders named GEO, RENDER, MASK, PARAM, UV_RENDER, UV_MASK, UV_NORMAL, and UV_POS. Note that you may need to list validation subjects to exclude from training in {path_to_training_data}/val.txt (this tutorial has only one subject and leave it empty). If you wish to render images with headless servers equipped with NVIDIA GPU, add -e to enable EGL rendering.
python -m apps.render_data -i {path_to_rp_dennis_posed_004_OBJ} -o {path_to_training_data} [-e]

Training (Linux Only)

Warning: the following code becomes extremely slow without pyembree. Please make sure you install pyembree.

  1. run the following script to train the shape module. The intermediate results and checkpoints are saved under ./results and ./checkpoints respectively. You can add --batch_size and --num_sample_input flags to adjust the batch size and the number of sampled points based on available GPU memory.
python -m apps.train_shape --dataroot {path_to_training_data} --random_flip --random_scale --random_trans
  1. run the following script to train the color module.
python -m apps.train_color --dataroot {path_to_training_data} --num_sample_inout 0 --num_sample_color 5000 --sigma 0.1 --random_flip --random_scale --random_trans

Related Research

Monocular Real-Time Volumetric Performance Capture (ECCV 2020)
Ruilong Li*, Yuliang Xiu*, Shunsuke Saito, Zeng Huang, Kyle Olszewski, Hao Li

The first real-time PIFu by accelerating reconstruction and rendering!!

PIFuHD: Multi-Level Pixel-Aligned Implicit Function for High-Resolution 3D Human Digitization (CVPR 2020)
Shunsuke Saito, Tomas Simon, Jason Saragih, Hanbyul Joo

We further improve the quality of reconstruction by leveraging multi-level approach!

ARCH: Animatable Reconstruction of Clothed Humans (CVPR 2020)
Zeng Huang, Yuanlu Xu, Christoph Lassner, Hao Li, Tony Tung

Learning PIFu in canonical space for animatable avatar generation!

Robust 3D Self-portraits in Seconds (CVPR 2020)
Zhe Li, Tao Yu, Chuanyu Pan, Zerong Zheng, Yebin Liu

They extend PIFu to RGBD + introduce "PIFusion" utilizing PIFu reconstruction for non-rigid fusion.

Learning to Infer Implicit Surfaces without 3d Supervision (NeurIPS 2019)
Shichen Liu, Shunsuke Saito, Weikai Chen, Hao Li

We answer to the question of "how can we learn implicit function if we don't have 3D ground truth?"

SiCloPe: Silhouette-Based Clothed People (CVPR 2019, best paper finalist)
Ryota Natsume*, Shunsuke Saito*, Zeng Huang, Weikai Chen, Chongyang Ma, Hao Li, Shigeo Morishima

Our first attempt to reconstruct 3D clothed human body with texture from a single image!

Deep Volumetric Video from Very Sparse Multi-view Performance Capture (ECCV 2018)
Zeng Huang, Tianye Li, Weikai Chen, Yajie Zhao, Jun Xing, Chloe LeGendre, Linjie Luo, Chongyang Ma, Hao Li

Implict surface learning for sparse view human performance capture!


For commercial queries, please contact:

Hao Li: [email protected] ccto: [email protected] Baker!!

[3DV 2021] A Dataset-Dispersion Perspective on Reconstruction Versus Recognition in Single-View 3D Reconstruction Networks

dispersion-score Official implementation of 3DV 2021 Paper A Dataset-dispersion Perspective on Reconstruction versus Recognition in Single-view 3D Rec

Yefan 7 May 28, 2022
PyTorch Code for "Generalization in Dexterous Manipulation via Geometry-Aware Multi-Task Learning"

Generalization in Dexterous Manipulation via Geometry-Aware Multi-Task Learning [Project Page] [Paper] Wenlong Huang1, Igor Mordatch2, Pieter Abbeel1,

Wenlong Huang 40 Nov 22, 2022
Deep-Learning-Book-Chapter-Summaries - Attempting to make the Deep Learning Book easier to understand.

Deep-Learning-Book-Chapter-Summaries This repository provides a summary for each chapter of the Deep Learning book by Ian Goodfellow, Yoshua Bengio an

Aman Dalmia 1k Dec 27, 2022
Experiments for Neural Flows paper

Neural Flows: Efficient Alternative to Neural ODEs [arxiv] TL;DR: We directly model the neural ODE solutions with neural flows, which is much faster a

54 Dec 07, 2022
PyTorch Lightning + Hydra. A feature-rich template for rapid, scalable and reproducible ML experimentation with best practices. ⚡🔥⚡

Lightning-Hydra-Template A clean and scalable template to kickstart your deep learning project 🚀 ⚡ 🔥 Click on Use this template to initialize new re

Łukasz Zalewski 2.1k Jan 09, 2023
VD-BERT: A Unified Vision and Dialog Transformer with BERT

VD-BERT: A Unified Vision and Dialog Transformer with BERT PyTorch Code for the following paper at EMNLP2020: Title: VD-BERT: A Unified Vision and Dia

Salesforce 44 Nov 01, 2022
🧑‍🔬 verify your TEAL program by experiment and observation

Graviton - Testing TEAL with Dry Runs Tutorial Local Installation The following instructions assume that you have make available in your local environ

Algorand 18 Jan 03, 2023
Regularized Frank-Wolfe for Dense CRFs: Generalizing Mean Field and Beyond

CRF - Conditional Random Fields A library for dense conditional random fields (CRFs). This is the official accompanying code for the paper Regularized

Đ.Khuê Lê-Huu 21 Nov 26, 2022
Code from Daniel Lemire, A Better Alternative to Piecewise Linear Time Series Segmentation

PiecewiseLinearTimeSeriesApproximation code from Daniel Lemire, A Better Alternative to Piecewise Linear Time Series Segmentation, SIAM Data Mining 20

Daniel Lemire 21 Oct 27, 2022
A user-friendly research and development tool built to standardize RL competency assessment for custom agents and environments.

Built with ❤️ by Sam Showalter Contents Overview Installation Dependencies Usage Scripts Standard Execution Environment Development Environment Benchm

SRI-AIC 1 Nov 18, 2021
Attentive Implicit Representation Networks (AIR-Nets)

Attentive Implicit Representation Networks (AIR-Nets) Preprint | Supplementary | Accepted at the International Conference on 3D Vision (3DV) teaser.mo

29 Dec 07, 2022
Learning hidden low dimensional dyanmics using a Generalized Onsager Principle and neural networks

OnsagerNet Learning hidden low dimensional dyanmics using a Generalized Onsager Principle and neural networks This is the original pyTorch implemenati

Haijun.Yu 3 Aug 24, 2022
Performance Analysis of Multi-user NOMA Wireless-Powered mMTC Networks: A Stochastic Geometry Approach

Performance Analysis of Multi-user NOMA Wireless-Powered mMTC Networks: A Stochastic Geometry Approach Thanh Luan Nguyen, Tri Nhu Do, Georges Kaddoum

Thanh Luan Nguyen 2 Oct 10, 2022
SAT: 2D Semantics Assisted Training for 3D Visual Grounding, ICCV 2021 (Oral)

SAT: 2D Semantics Assisted Training for 3D Visual Grounding SAT: 2D Semantics Assisted Training for 3D Visual Grounding by Zhengyuan Yang, Songyang Zh

Zhengyuan Yang 22 Nov 30, 2022
ImageBART: Bidirectional Context with Multinomial Diffusion for Autoregressive Image Synthesis

ImageBART NeurIPS 2021 Patrick Esser*, Robin Rombach*, Andreas Blattmann*, Björn Ommer * equal contribution arXiv | BibTeX | Poster Requirements A sui

CompVis Heidelberg 110 Jan 01, 2023
LSTMs (Long Short Term Memory) RNN for prediction of price trends

Price Prediction with Recurrent Neural Networks LSTMs BTC-USD price prediction with deep learning algorithm. Artificial Neural Networks specifically L

5 Nov 12, 2021
Evaluation suite for large-scale language models.

This repo contains code for running the evaluations and reproducing the results from the Jurassic-1 Technical Paper (see blog post), with current support for running the tasks through both the AI21 S

71 Dec 17, 2022
E-Ink Magic Calendar that automatically syncs to Google Calendar and runs off a battery powered Raspberry Pi Zero

MagInkCal This repo contains the code needed to drive an E-Ink Magic Calendar that uses a battery powered (PiSugar2) Raspberry Pi Zero WH to retrieve

2.8k Dec 28, 2022
TLXZoo - Pre-trained models based on TensorLayerX

Pre-trained models based on TensorLayerX. TensorLayerX is a multi-backend AI fra

TensorLayer Community 13 Dec 07, 2022
Short and long time series classification using convolutional neural networks

time-series-classification Short and long time series classification via convolutional neural networks In this project, we present a novel framework f

35 Oct 22, 2022