# Intrinsic Image Transfer for Illumination Manipulation

arXiv: https://arxiv.org/abs/2107.00704 · HTML: https://mlsanity.com/paper/2107.00704/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 23 of its 76 references that are in the map.
- First posted on arXiv 1 Jul 2021.

## Builds on (most cited first, 23 of 23)

- [The Cityscapes Dataset for Semantic Urban Scene Understanding](https://mlsanity.com/paper/1604.01685/) (2016)
- [Arbitrary Style Transfer in Real-time with Adaptive Instance Normalization](https://mlsanity.com/paper/1703.06868/) (2017)
- [Deep Retinex Decomposition for Low-Light Enhancement](https://mlsanity.com/paper/1808.04560/) (2018)
- [Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks](https://mlsanity.com/paper/1703.10593/) (2017)
- [Zero-Reference Deep Curve Estimation for Low-Light Image Enhancement](https://mlsanity.com/paper/2001.06826/) (2020)
- [EnlightenGAN: Deep Light Enhancement without Paired Supervision](https://mlsanity.com/paper/1906.06972/) (2019)
- [Learning to See in the Dark](https://mlsanity.com/paper/1805.01934/) (2018)
- [NIMA: Neural Image Assessment](https://mlsanity.com/paper/1709.05424/) (2017)
- [Universal Style Transfer via Feature Transforms](https://mlsanity.com/paper/1705.08086/) (2017)
- [Neural Style Transfer: A Review](https://mlsanity.com/paper/1705.04058/) (2017)
- [Photorealistic Style Transfer via Wavelet Transforms](https://mlsanity.com/paper/1903.09760/) (2019)
- [Learning to Predict Indoor Illumination from a Single Image](https://mlsanity.com/paper/1704.00090/) (2017)
- [DSLR-Quality Photos on Mobile Devices with Deep Convolutional Networks](https://mlsanity.com/paper/1704.02470/) (2017)
- [Learning Intrinsic Image Decomposition from Watching the World](https://mlsanity.com/paper/1804.00582/) (2018)
- [Deep Outdoor Illumination Estimation](https://mlsanity.com/paper/1611.06403/) (2016)
- [Self-Supervised Intrinsic Image Decomposition](https://mlsanity.com/paper/1711.03678/) (2017)
- [A Closed-form Solution to Universal Style Transfer](https://mlsanity.com/paper/1906.00668/) (2019)
- [Direct Intrinsics: Learning Albedo-Shading Decomposition by Convolutional Regression](https://mlsanity.com/paper/1512.02311/) (2015)
- [LIME: Live Intrinsic Material Estimation](https://mlsanity.com/paper/1801.01075/) (2018)
- [WESPE: Weakly Supervised Photo Enhancer for Digital Cameras](https://mlsanity.com/paper/1709.01118/) (2017)
- [Intrinsic Image Transformation via Scale Space Decomposition](https://mlsanity.com/paper/1805.10253/) (2018)
- [Radiometric Scene Decomposition: Scene Reflectance, Illumination, and Geometry from RGB-D Images](https://mlsanity.com/paper/1604.01354/) (2016)
- [Multispectral Image Intrinsic Decomposition via Low Rank Constraint](https://mlsanity.com/paper/1802.08793/) (2018)

## Built on by (most cited first, 1 of 1)

- [Optimal Image Transport on Sparse Dictionaries](https://mlsanity.com/paper/2311.01984/) (2023)

## Abstract (arXiv)

This paper presents a novel intrinsic image transfer (IIT) algorithm for illumination manipulation, which creates a local image translation between two illumination surfaces. This model is built on an optimization-based framework consisting of three photo-realistic losses defined on the sub-layers factorized by an intrinsic image decomposition. We illustrate that all losses can be reduced without the necessity of taking an intrinsic image decomposition under the well-known spatial-varying illumination illumination-invariant reflectance prior knowledge. Moreover, with a series of relaxations, all of them can be directly defined on images, giving a closed-form solution for image illumination manipulation. This new paradigm differs from the prevailing Retinex-based algorithms, as it provides an implicit way to deal with the per-pixel image illumination. We finally demonstrate its versatility and benefits to the illumination-related tasks such as illumination compensation, image enhancement, and high dynamic range (HDR) image compression, and show the high-quality results on natural image datasets.