# Self-Supervised Intrinsic Image Decomposition Network Considering Reflectance Consistency

arXiv: https://arxiv.org/abs/2111.04506 · HTML: https://mlsanity.com/paper/2111.04506/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 11 of its 30 references that are in the map.
- First posted on arXiv 5 Nov 2021.

## Builds on (most cited first, 11 of 11)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift](https://mlsanity.com/paper/1502.03167/) (2015)
- [Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification](https://mlsanity.com/paper/1502.01852/) (2015)
- [CGIntrinsics: Better Intrinsic Image Decomposition through Physically-Based Rendering](https://mlsanity.com/paper/1808.08601/) (2018)
- [Learning Intrinsic Image Decomposition from Watching the World](https://mlsanity.com/paper/1804.00582/) (2018)
- [Unsupervised Learning for Intrinsic Image Decomposition from a Single Image](https://mlsanity.com/paper/1911.09930/) (2019)
- [Learning Data-driven Reflectance Priors for Intrinsic Image Decomposition](https://mlsanity.com/paper/1510.02413/) (2015)
- [Unsupervised Deep Single-Image Intrinsic Decomposition using Illumination-Varying Image Sequences](https://mlsanity.com/paper/1803.00805/) (2018)
- [Scene Segmentation-Based Luminance Adjustment for Multi-Exposure Image Fusion](https://mlsanity.com/paper/1903.07428/) (2019)
- [A Retinex-based Image Enhancement Scheme with Noise Aware Shadow-up Function](https://mlsanity.com/paper/1811.03280/) (2018)

## Abstract (arXiv)

We propose a novel intrinsic image decomposition network considering reflectance consistency. Intrinsic image decomposition aims to decompose an image into illumination-invariant and illumination-variant components, referred to as ``reflectance'' and ``shading,'' respectively. Although there are three consistencies that the reflectance and shading should satisfy, most conventional work does not sufficiently account for consistency with respect to reflectance, owing to the use of a white-illuminant decomposition model and the lack of training images capturing the same objects under various illumination-brightness and -color conditions. For this reason, the three consistencies are considered in the proposed network by using a color-illuminant model and training the network with losses calculated from images taken under various illumination conditions. In addition, the proposed network can be trained in a self-supervised manner because various illumination conditions can easily be simulated. Experimental results show that our network can decompose images into reflectance and shading components.