SHADeS: Self-supervised Monocular Depth Estimation Through Non-Lambertian Image Decomposition

TL;DR

This paper introduces SHADeS, a self-supervised model for monocular depth estimation in colonoscopy images that effectively decouples light and depth, especially handling specular reflections, improving robustness in challenging visual conditions.

Contribution

It proposes a non-Lambertian, self-supervised approach that jointly estimates shading, albedo, depth, and specularities, advancing depth estimation in specular-rich colonoscopy scenes.

Findings

SHADeS outperforms previous models in specular regions

The model is robust on real colonoscopy images and phantom data

Joint light decomposition improves depth estimation accuracy

Abstract

Purpose: Visual 3D scene reconstruction can support colonoscopy navigation. It can help in recognising which portions of the colon have been visualised and characterising the size and shape of polyps. This is still a very challenging problem due to complex illumination variations, including abundant specular reflections. We investigate how to effectively decouple light and depth in this problem. Methods: We introduce a self-supervised model that simultaneously characterises the shape and lighting of the visualised colonoscopy scene. Our model estimates shading, albedo, depth, and specularities (SHADeS) from single images. Unlike previous approaches (IID), we use a non-Lambertian model that treats specular reflections as a separate light component. The implementation of our method is available at https://github.com/RemaDaher/SHADeS. Results: We demonstrate on real colonoscopy images (Hyper Kvasir) that previous models for light decomposition (IID) and depth estimation (MonoVIT, ModoDepth2) are negatively affected by specularities. In contrast, SHADeS can simultaneously produce light decomposition and depth maps that are robust to specular regions. We also perform a quantitative comparison on phantom data (C3VD) where we further demonstrate the robustness of our model. Conclusion: Modelling specular reflections improves depth estimation in colonoscopy. We propose an effective self-supervised approach that uses this insight to jointly estimate light decomposition and depth. Light decomposition has the potential to help with other problems, such as place recognition within the colon.