Label Denoising Adversarial Network (LDAN) for Inverse Lighting of Face Images

09/06/2017
by   Hao Zhou, et al.
0

Lighting estimation from face images is an important task and has applications in many areas such as image editing, intrinsic image decomposition, and image forgery detection. We propose to train a deep Convolutional Neural Network (CNN) to regress lighting parameters from a single face image. Lacking massive ground truth lighting labels for face images in the wild, we use an existing method to estimate lighting parameters, which are treated as ground truth with unknown noises. To alleviate the effect of such noises, we utilize the idea of Generative Adversarial Networks (GAN) and propose a Label Denoising Adversarial Network (LDAN) to make use of synthetic data with accurate ground truth to help train a deep CNN for lighting regression on real face images. Experiments show that our network outperforms existing methods in producing consistent lighting parameters of different faces under similar lighting conditions. Moreover, our method is 100,000 times faster in execution time than prior optimization-based lighting estimation approaches.

READ FULL TEXT

page 7

page 13

page 15

research
02/18/2019

Decomposing multispectral face images into diffuse and specular shading and biophysical parameters

We propose a novel biophysical and dichromatic reflectance model that ef...
research
09/07/2021

Brand Label Albedo Extraction of eCommerce Products using Generative Adversarial Network

In this paper we present our solution to extract albedo of branded label...
research
01/17/2023

Face Inverse Rendering via Hierarchical Decoupling

Previous face inverse rendering methods often require synthetic data wit...
research
08/26/2023

Neural Implicit Morphing of Face Images

Face morphing is one of the seminal problems in computer graphics, with ...
research
04/19/2023

DiFaReli: Diffusion Face Relighting

We present a novel approach to single-view face relighting in the wild. ...
research
07/07/2020

Learning Model-Blind Temporal Denoisers without Ground Truths

Denoisers trained with synthetic data often fail to cope with the divers...
research
10/21/2019

Batch Face Alignment using a Low-rank GAN

This paper studies the problem of aligning a set of face images of the s...

Please sign up or login with your details

Forgot password? Click here to reset