《Towards High Fidelity Face Relighting with Realistic Shadows》(CVPR 2021)

Overview

Towards High Fidelity Face-Relighting with Realistic Shadows

Andrew Hou, Ze Zhang, Michel Sarkis, Ning Bi, Yiying Tong, Xiaoming Liu. In CVPR, 2021.

alt text alt text

The code for this project was developed using Python 3 and Tensorflow 1.9.0.

Trained model

To run our trained model on an input image and a target lighting:

python test_relight_single_image.py input_image_path target_lighting_path output_image_path gpu_id

An example of this is provided below:

python test_relight_single_image.py sample_images/01503.png sample_lightings/light_left.txt sample_outputs/01503_left.png 7

Citation

If you utilize our code in your work, please cite our CVPR 2021 paper.

@inproceedings{ towards-high-fidelity-face-relighting-with-realistic-shadows,
  author = { Andrew Hou and Ze Zhang and Michel Sarkis and Ning Bi and Yiying Tong and Xiaoming Liu },
  title = { Towards High Fidelity Face Relighting with Realistic Shadows },
  booktitle={IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = { 2021 }
}

Contact

If there are any questions, please feel free to post here or contact the authors at {houandr1, zhangze6, ytong, liuxm}@msu.edu, {msarkis, nbi}@qti.qualcomm.com

You might also like...
Implementation for HFGI: High-Fidelity GAN Inversion for Image Attribute Editing
Implementation for HFGI: High-Fidelity GAN Inversion for Image Attribute Editing

HFGI: High-Fidelity GAN Inversion for Image Attribute Editing High-Fidelity GAN Inversion for Image Attribute Editing Update: We released the inferenc

 SCI-AIDE : High-fidelity Few-shot Histopathology Image Synthesis for Rare Cancer Diagnosis
SCI-AIDE : High-fidelity Few-shot Histopathology Image Synthesis for Rare Cancer Diagnosis

SCI-AIDE : High-fidelity Few-shot Histopathology Image Synthesis for Rare Cancer Diagnosis Pretrained Models In this work, we created synthetic tissue

PyTorch Implementation of DiffGAN-TTS: High-Fidelity and Efficient Text-to-Speech with Denoising Diffusion GANs
PyTorch Implementation of DiffGAN-TTS: High-Fidelity and Efficient Text-to-Speech with Denoising Diffusion GANs

DiffGAN-TTS - PyTorch Implementation PyTorch implementation of DiffGAN-TTS: High

Parallel and High-Fidelity Text-to-Lip Generation; AAAI 2022 ; Official code

Parallel and High-Fidelity Text-to-Lip Generation This repository is the official PyTorch implementation of our AAAI-2022 paper, in which we propose P

 From Fidelity to Perceptual Quality: A Semi-Supervised Approach for Low-Light Image Enhancement (CVPR'2020)
From Fidelity to Perceptual Quality: A Semi-Supervised Approach for Low-Light Image Enhancement (CVPR'2020)

Under-exposure introduces a series of visual degradation, i.e. decreased visibility, intensive noise, and biased color, etc. To address these problems, we propose a novel semi-supervised learning approach for low-light image enhancement.

《Deep Single Portrait Image Relighting》(ICCV 2019)

Ratio Image Based Rendering for Deep Single-Image Portrait Relighting [Project Page] This is part of the Deep Portrait Relighting project. If you find

This is the implementation of the paper "Self-supervised Outdoor Scene Relighting"

Self-supervised Outdoor Scene Relighting This is the implementation of the paper "Self-supervised Outdoor Scene Relighting". The model is implemented

Code for PhySG: Inverse Rendering with Spherical Gaussians for Physics-based Relighting and Material Editing

PhySG: Inverse Rendering with Spherical Gaussians for Physics-based Relighting and Material Editing CVPR 2021. Project page: https://kai-46.github.io/

Official implementation of the paper 'Details or Artifacts: A Locally Discriminative Learning Approach to Realistic Image Super-Resolution' in CVPR 2022
Official implementation of the paper 'Details or Artifacts: A Locally Discriminative Learning Approach to Realistic Image Super-Resolution' in CVPR 2022

LDL Paper | Supplementary Material Details or Artifacts: A Locally Discriminative Learning Approach to Realistic Image Super-Resolution Jie Liang*, Hu

Comments
  • The process to create lighting from reference image

    The process to create lighting from reference image

    Hi, thanks for the great work. I would like to ask you a few questions about the lighting transfer.

    1. How can I transfer the light from the source to the reference image?
    2. Do I need other methods to perform the lighting direction estimation? I tried the EstimationLightDir.m and it outputs 8 envir_map.csv files, I don't know the meaning of those 8 files and the next step. Could you show and explain to me the step to doing this?

    Thanks

    opened by XezXey 3
  • Face normal retrieval

    Face normal retrieval

    Hi, thanks for the amazing work! I wondered can the work extract the face normals of the target face? And can you provide a script or some advice? Thanks in advance!

    opened by FeiiYin 2
  • Can it run 1024 resolution images?

    Can it run 1024 resolution images?

    Thank you for letting me come across code that works so well, my goal is to run 1024 resolution images, how do I do that? Very much looking forward to your reply!

    opened by a656418zz 1
  • About trainning examples

    About trainning examples

    Hi! I'm very interested in your paper and project, but I encountered some issues when I try to set up the environment for the training example. Could you send me the result of the training example? I'm very interested in that. My email is [email protected]. Thank you!

    opened by WangyuanhaoNB 1
Owner
null
Disentangled Cycle Consistency for Highly-realistic Virtual Try-On, CVPR 2021

Disentangled Cycle Consistency for Highly-realistic Virtual Try-On, CVPR 2021 [WIP] The code for CVPR 2021 paper 'Disentangled Cycle Consistency for H

ChongjianGE 94 Dec 11, 2022
Deep generative modeling for time-stamped heterogeneous data, enabling high-fidelity models for a large variety of spatio-temporal domains.

Neural Spatio-Temporal Point Processes [arxiv] Ricky T. Q. Chen, Brandon Amos, Maximilian Nickel Abstract. We propose a new class of parameterizations

Facebook Research 75 Dec 19, 2022
HiFi-GAN: High Fidelity Denoising and Dereverberation Based on Speech Deep Features in Adversarial Networks

HiFiGAN Denoiser This is a Unofficial Pytorch implementation of the paper HiFi-GAN: High Fidelity Denoising and Dereverberation Based on Speech Deep F

Rishikesh (ऋषिकेश) 134 Dec 27, 2022
HiFi-GAN: Generative Adversarial Networks for Efficient and High Fidelity Speech Synthesis

HiFi-GAN: Generative Adversarial Networks for Efficient and High Fidelity Speech Synthesis Jungil Kong, Jaehyeon Kim, Jaekyoung Bae In our paper, we p

Rishikesh (ऋषिकेश) 31 Dec 8, 2022
Tensorflow python implementation of "Learning High Fidelity Depths of Dressed Humans by Watching Social Media Dance Videos"

Learning High Fidelity Depths of Dressed Humans by Watching Social Media Dance Videos This repository is the official tensorflow python implementation

Yasamin Jafarian 287 Jan 6, 2023
UnivNet: A Neural Vocoder with Multi-Resolution Spectrogram Discriminators for High-Fidelity Waveform Generation

UnivNet UnivNet: A Neural Vocoder with Multi-Resolution Spectrogram Discriminators for High-Fidelity Waveform Generation. Training python train.py --c

Rishikesh (ऋषिकेश) 55 Dec 26, 2022
Unofficial PyTorch Implementation of UnivNet: A Neural Vocoder with Multi-Resolution Spectrogram Discriminators for High-Fidelity Waveform Generation

UnivNet UnivNet: A Neural Vocoder with Multi-Resolution Spectrogram Discriminators for High-Fidelity Waveform Generation This is an unofficial PyTorch

MINDs Lab 170 Jan 4, 2023
This repository contains the code for using the H3DS dataset introduced in H3D-Net: Few-Shot High-Fidelity 3D Head Reconstruction

H3DS Dataset This repository contains the code for using the H3DS dataset introduced in H3D-Net: Few-Shot High-Fidelity 3D Head Reconstruction Access

Crisalix 72 Dec 10, 2022
Unofficial PyTorch Implementation of UnivNet: A Neural Vocoder with Multi-Resolution Spectrogram Discriminators for High-Fidelity Waveform Generation

UnivNet UnivNet: A Neural Vocoder with Multi-Resolution Spectrogram Discriminators for High-Fidelity Waveform Generation This is an unofficial PyTorch

MINDs Lab 54 Aug 30, 2021
A two-stage U-Net for high-fidelity denoising of historical recordings

A two-stage U-Net for high-fidelity denoising of historical recordings Official repository of the paper (not submitted yet): E. Moliner and V. Välimäk

Eloi Moliner Juanpere 57 Jan 5, 2023