SeeClear: Reliable Transparent Object Depth Estimation via Generative Opacification
This addresses a specific challenge in computer vision for applications like robotics and augmented reality, but it is incremental as it builds on existing depth estimation methods.
The paper tackles the problem of unreliable monocular depth estimation for transparent objects by proposing SeeClear, a framework that converts transparent objects into opaque images using a generative opacification module, enabling stable depth predictions without retraining existing estimators. Experiments on synthetic and real-world datasets show significant improvements in depth estimation for transparent objects.
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/