SeeClear: Reliable Transparent Object Depth Estimation via Generative Opacification

2026-03-19

AI Summary

Monocular depth estimation fails on transparent objects due to refraction and transmission effects, leading to unstable predictions. This work proposes SeeClear, a novel framework that introduces a generative opacification strategy: leveraging a diffusion model to transform transparent regions into geometrically consistent opaque images, which are then fed into off-the-shelf depth estimators without requiring any model modification or retraining. To enable this approach, we construct SeeClear-396k, a large-scale synthetic dataset specifically designed for training. Experimental results demonstrate that our method significantly improves both accuracy and robustness in depth estimation for transparent objects across synthetic and real-world scenes.

Technology Category

• Computer Vision: Interpretability, Explainability, and Transparency
• Machine Learning: Transparent, Interpretable, Explainable ML
• Search and Optimization: Non-convex Optimization

Application Category

• Security and Privacy: Data transparency and provenance
• Responsible Web: Algorithmic accountability and transparency on the web
• User Modeling, Personalization and Recommendation: Accountability, Transparency, and Ethics for personalization

Abstract

Monocular depth estimation remains challenging for transparent objects, where refraction and transmission are difficult to model and break the appearance assumptions used by depth networks. As a result, state-of-the-art estimators often produce unstable or incorrect depth predictions for transparent materials. We propose SeeClear, a novel framework that converts transparent objects into generative opaque images, enabling stable monocular depth estimation for transparent objects. Given an input image, we first localize transparent regions and transform their refractive appearance into geometrically consistent opaque shapes using a diffusion-based generative opacification module. The processed image is then fed into an off-the-shelf monocular depth estimator without retraining or architectural changes. To train the opacification model, we construct SeeClear-396k, a synthetic dataset containing 396k paired transparent-opaque renderings. Experiments on both synthetic and real-world datasets show that SeeClear significantly improves depth estimation for transparent objects. Project page: https://heyumeng.com/SeeClear-web/

Problem

• transparent object
• monocular depth estimation
• refraction
• depth prediction
• appearance assumption

Innovation

• generative opacification
• transparent object depth estimation
• diffusion-based generation
• monocular depth estimation
• synthetic dataset