# Deep intrinsic decomposition trained on surreal scenes yet with realistic light effects

arXiv: https://arxiv.org/abs/2009.06295 · HTML: https://mlsanity.com/paper/2009.06295/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 14 Sep 2020.

## Built on by (most cited first, 3 of 3)

- [Relighting from a Single Image: Datasets and Deep Intrinsic-based Architecture](https://mlsanity.com/paper/2409.18770/) (2024)
- [Discriminative feature encoding for intrinsic image decomposition](https://mlsanity.com/paper/2209.12155/) (2022)
- [Invariant Descriptors for Intrinsic Reflectance Optimization](https://mlsanity.com/paper/2204.04076/) (2022)

## Abstract (arXiv)

Estimation of intrinsic images still remains a challenging task due to weaknesses of ground-truth datasets, which either are too small or present non-realistic issues. On the other hand, end-to-end deep learning architectures start to achieve interesting results that we believe could be improved if important physical hints were not ignored. In this work, we present a twofold framework: (a) a flexible generation of images overcoming some classical dataset problems such as larger size jointly with coherent lighting appearance; and (b) a flexible architecture tying physical properties through intrinsic losses. Our proposal is versatile, presents low computation time, and achieves state-of-the-art results.