An Optical physics inspired CNN approach for intrinsic image decomposition

05/21/2021
by   Harshana Weligampola, et al.
0

Intrinsic Image Decomposition is an open problem of generating the constituents of an image. Generating reflectance and shading from a single image is a challenging task specifically when there is no ground truth. There is a lack of unsupervised learning approaches for decomposing an image into reflectance and shading using a single image. We propose a neural network architecture capable of this decomposition using physics-based parameters derived from the image. Through experimental results, we show that (a) the proposed methodology outperforms the existing deep learning-based IID techniques and (b) the derived parameters improve the efficacy significantly. We conclude with a closer analysis of the results (numerical and example images) showing several avenues for improvement.

READ FULL TEXT

page 2

page 4

research
11/10/2017

Self-Supervised Intrinsic Image Decomposition

Intrinsic decomposition from a single image is a highly challenging task...
research
03/07/2016

From A to Z: Supervised Transfer of Style and Content Using Deep Neural Network Generators

We propose a new neural network architecture for solving single-image an...
research
12/04/2017

CNN based Learning using Reflection and Retinex Models for Intrinsic Image Decomposition

Most of the traditional work on intrinsic image decomposition rely on de...
research
09/03/2020

Physics-based Shading Reconstruction for Intrinsic Image Decomposition

We investigate the use of photometric invariance and deep learning to co...
research
12/23/2016

DARN: a Deep Adversial Residual Network for Intrinsic Image Decomposition

We present a new deep supervised learning method for intrinsic decomposi...
research
07/30/2018

Deep Hybrid Real and Synthetic Training for Intrinsic Decomposition

Intrinsic image decomposition is the process of separating the reflectan...
research
05/05/2021

Physically Inspired Dense Fusion Networks for Relighting

Image relighting has emerged as a problem of significant research intere...

Please sign up or login with your details

Forgot password? Click here to reset