SeeClear: Reliable Transparent Object Depth Estimation via Generative Opacification

TL;DR

SeeClear introduces a generative opacification approach that transforms transparent objects into opaque images, enabling more reliable monocular depth estimation without retraining existing models.

Contribution

The paper presents a novel framework that converts transparent objects into opaque images using diffusion-based generative models, improving depth estimation accuracy.

Findings

Significant improvement in depth accuracy for transparent objects.

Effective generalization to real-world datasets.

No need for retraining existing depth estimation models.

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/