# Unsupervised Intrinsic Image Decomposition with LiDAR Intensity

arXiv: https://arxiv.org/abs/2303.10820 · HTML: https://mlsanity.com/paper/2303.10820/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 16 of its 50 references that are in the map.
- First posted on arXiv 20 Mar 2023.

## Builds on (most cited first, 16 of 16)

- [Generative Adversarial Networks](https://mlsanity.com/paper/2203.00667/) (2022)
- [ShapeNet: An Information-Rich 3D Model Repository](https://mlsanity.com/paper/1512.03012/) (2015)
- [Deep Image Prior](https://mlsanity.com/paper/1711.10925/) (2017)
- [Autoencoding beyond pixels using a learned similarity metric](https://mlsanity.com/paper/1512.09300/) (2015)
- [Deep Depth Completion of a Single RGB-D Image](https://mlsanity.com/paper/1803.09326/) (2018)
- [InverseRenderNet: Learning single image inverse rendering](https://mlsanity.com/paper/1811.12328/) (2018)
- [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)
- [Self-Supervised Intrinsic Image Decomposition](https://mlsanity.com/paper/1711.03678/) (2017)
- [Direct Intrinsics: Learning Albedo-Shading Decomposition by Convolutional Regression](https://mlsanity.com/paper/1512.02311/) (2015)
- [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)
- [Reflectance Adaptive Filtering Improves Intrinsic Image Estimation](https://mlsanity.com/paper/1612.05062/) (2016)
- [Deep Retinex Network for Estimating Illumination Colors with Self-Supervised Learning](https://mlsanity.com/paper/2102.04003/) (2021)
- [DeRenderNet: Intrinsic Image Decomposition of Urban Scenes with Shape-(In)dependent Shading Rendering](https://mlsanity.com/paper/2104.13602/) (2021)

## Built on by (most cited first, 6 of 6)

- [VT-Intrinsic: Physics-Based Decomposition of Reflectance and Shading using a Single Visible-Thermal Image Pair](https://mlsanity.com/paper/2509.10388/) (2025)
- [Intrinsic Image Decomposition Using Point Cloud Representation](https://mlsanity.com/paper/2307.10924/) (2023)
- [Unsupervised Intrinsic Image Decomposition with LiDAR Intensity Enhanced Training](https://mlsanity.com/paper/2403.14089/) (2024)
- [Objective, Absolute and Hue-aware Metrics for Intrinsic Image Decomposition on Real-World Scenes: A Proof of Concept](https://mlsanity.com/paper/2505.19500/) (2025)
- [IPCD: Intrinsic Point-Cloud Decomposition](https://mlsanity.com/paper/2511.09866/) (2025)
- [Sub-Footprint Effect Correction in FW-LiDAR Point Clouds via Intra-Footprint Target Unmixing](https://mlsanity.com/paper/2605.09845/) (2026)

## Abstract (arXiv)

Intrinsic image decomposition (IID) is the task that decomposes a natural image into albedo and shade. While IID is typically solved through supervised learning methods, it is not ideal due to the difficulty in observing ground truth albedo and shade in general scenes. Conversely, unsupervised learning methods are currently underperforming supervised learning methods since there are no criteria for solving the ill-posed problems. Recently, light detection and ranging (LiDAR) is widely used due to its ability to make highly precise distance measurements. Thus, we have focused on the utilization of LiDAR, especially LiDAR intensity, to address this issue. In this paper, we propose unsupervised intrinsic image decomposition with LiDAR intensity (IID-LI). Since the conventional unsupervised learning methods consist of image-to-image transformations, simply inputting LiDAR intensity is not an effective approach. Therefore, we design an intensity consistency loss that computes the error between LiDAR intensity and gray-scaled albedo to provide a criterion for the ill-posed problem. In addition, LiDAR intensity is difficult to handle due to its sparsity and occlusion, hence, a LiDAR intensity densification module is proposed. We verified the estimating quality using our own dataset, which include RGB images, LiDAR intensity and human judged annotations. As a result, we achieved an estimation accuracy that outperforms conventional unsupervised learning methods. Dataset link : (https://github.com/ntthilab-cv/NTT-intrinsic-dataset).