# Intrinsic Image Decomposition for Robust Self-supervised Monocular Depth Estimation on Reflective Surfaces

arXiv: https://arxiv.org/abs/2503.22209 · HTML: https://mlsanity.com/paper/2503.22209/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 20 of its 46 references that are in the map.
- First posted on arXiv 28 Mar 2025.

## Builds on (most cited first, 20 of 20)

- [ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenes](https://mlsanity.com/paper/1702.04405/) (2017)
- [Depth Map Prediction from a Single Image using a Multi-Scale Deep Network](https://mlsanity.com/paper/1406.2283/) (2014)
- [Unsupervised Monocular Depth Estimation with Left-Right Consistency](https://mlsanity.com/paper/1609.03677/) (2016)
- [Unsupervised Learning of Depth and Ego-Motion from Video](https://mlsanity.com/paper/1704.07813/) (2017)
- [3D Packing for Self-Supervised Monocular Depth Estimation](https://mlsanity.com/paper/1905.02693/) (2019)
- [On the uncertainty of self-supervised monocular depth estimation](https://mlsanity.com/paper/2005.06209/) (2020)
- [RGBleftrightarrowX: Image decomposition and synthesis using material- and lighting-aware diffusion models](https://mlsanity.com/paper/2405.00666/) (2024)
- [MonoViT: Self-Supervised Monocular Depth Estimation with a Vision Transformer](https://mlsanity.com/paper/2208.03543/) (2022)
- [HR-Depth: High Resolution Self-Supervised Monocular Depth Estimation](https://mlsanity.com/paper/2012.07356/) (2020)
- [InverseRenderNet: Learning single image inverse rendering](https://mlsanity.com/paper/1811.12328/) (2018)
- [Multi-view Depth Estimation using Epipolar Spatio-Temporal Networks](https://mlsanity.com/paper/2011.13118/) (2020)
- [Robust Monocular Depth Estimation under Challenging Conditions](https://mlsanity.com/paper/2308.09711/) (2023)
- [Intrinsic Image Decomposition via Ordinal Shading](https://mlsanity.com/paper/2311.12792/) (2023)
- [Learning Non-Lambertian Object Intrinsics across ShapeNet Categories](https://mlsanity.com/paper/1612.08510/) (2016)
- [Full Surround Monodepth from Multiple Cameras](https://mlsanity.com/paper/2104.00152/) (2021)
- [Self-supervised Monocular Depth Estimation: Let's Talk About The Weather](https://mlsanity.com/paper/2307.08357/) (2023)
- [Learning Depth Estimation for Transparent and Mirror Surfaces](https://mlsanity.com/paper/2307.15052/) (2023)
- [Direct Intrinsics: Learning Albedo-Shading Decomposition by Convolutional Regression](https://mlsanity.com/paper/1512.02311/) (2015)
- [Booster: a Benchmark for Depth from Images of Specular and Transparent Surfaces](https://mlsanity.com/paper/2301.08245/) (2023)
- [Unified Depth Prediction and Intrinsic Image Decomposition from a Single Image via Joint Convolutional Neural Fields](https://mlsanity.com/paper/1603.06359/) (2016)

## Abstract (arXiv)

Self-supervised monocular depth estimation (SSMDE) has gained attention in the field of deep learning as it estimates depth without requiring ground truth depth maps. This approach typically uses a photometric consistency loss between a synthesized image, generated from the estimated depth, and the original image, thereby reducing the need for extensive dataset acquisition. However, the conventional photometric consistency loss relies on the Lambertian assumption, which often leads to significant errors when dealing with reflective surfaces that deviate from this model. To address this limitation, we propose a novel framework that incorporates intrinsic image decomposition into SSMDE. Our method synergistically trains for both monocular depth estimation and intrinsic image decomposition. The accurate depth estimation facilitates multi-image consistency for intrinsic image decomposition by aligning different view coordinate systems, while the decomposition process identifies reflective areas and excludes corrupted gradients from the depth training process. Furthermore, our framework introduces a pseudo-depth generation and knowledge distillation technique to further enhance the performance of the student model across both reflective and non-reflective surfaces. Comprehensive evaluations on multiple datasets show that our approach significantly outperforms existing SSMDE baselines in depth prediction, especially on reflective surfaces.