# Intrinsic Image Transformation via Scale Space Decomposition

arXiv: https://arxiv.org/abs/1805.10253 · HTML: https://mlsanity.com/paper/1805.10253/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 25 May 2018.

## Built on by (most cited first, 10 of 10)

- [Intrinsic Image Decomposition via Ordinal Shading](https://mlsanity.com/paper/2311.12792/) (2023)
- [A Survey on Intrinsic Images: Delving Deep Into Lambert and Beyond](https://mlsanity.com/paper/2112.03842/) (2021)
- [PIE-Net: Photometric Invariant Edge Guided Network for Intrinsic Image Decomposition](https://mlsanity.com/paper/2203.16670/) (2022)
- [IBL-NeRF: Image-Based Lighting Formulation of Neural Radiance Fields](https://mlsanity.com/paper/2210.08202/) (2022)
- [Compound Batch Normalization for Long-tailed Image Classification](https://mlsanity.com/paper/2212.01007/) (2022)
- [Intrinsic Image Transfer for Illumination Manipulation](https://mlsanity.com/paper/2107.00704/) (2021)
- [Parameterization of Cross-Token Relations with Relative Positional Encoding for Vision MLP](https://mlsanity.com/paper/2207.07284/) (2022)
- [Learning Intrinsic Images for Clothing](https://mlsanity.com/paper/2111.08521/) (2021)
- [Intrinsic Image Decomposition Using Point Cloud Representation](https://mlsanity.com/paper/2307.10924/) (2023)
- [Hyperspectral Intrinsic Decomposition: Joint Recovery of Reflectance and Photometric Components for Non-Lambertian Scenes](https://mlsanity.com/paper/2607.25371/) (2026)

## Abstract (arXiv)

We introduce a new network structure for decomposing an image into its intrinsic albedo and shading. We treat this as an image-to-image transformation problem and explore the scale space of the input and output. By expanding the output images (albedo and shading) into their Laplacian pyramid components, we develop a multi-channel network structure that learns the image-to-image transformation function in successive frequency bands in parallel, within each channel is a fully convolutional neural network with skip connections. This network structure is general and extensible, and has demonstrated excellent performance on the intrinsic image decomposition problem. We evaluate the network on two benchmark datasets: the MPI-Sintel dataset and the MIT Intrinsic Images dataset. Both quantitative and qualitative results show our model delivers a clear progression over state-of-the-art.