Internal-External Boundary Attention Fusion for Glass Surface Segmentation

TL;DR

This paper introduces a novel boundary attention fusion method for glass surface segmentation, leveraging internal and external boundary features to improve detection accuracy in challenging visual conditions.

Contribution

The paper proposes separated internal-external boundary attention modules that individually learn and integrate visual features for better glass surface segmentation.

Findings

Outperforms state-of-the-art methods on six benchmarks.

Effectively captures boundary features for transparent object detection.

Demonstrates robustness in challenging visual scenarios.

Abstract

Glass surfaces of transparent objects and mirrors are not able to be uniquely and explicitly characterized by their visual appearances because they contain the visual appearance of other reflected or transmitted surfaces as well. Detecting glass regions from a single-color image is a challenging task. Recent deep-learning approaches have paid attention to the description of glass surface boundary where the transition of visual appearances between glass and non-glass surfaces are observed. In this work, we analytically investigate how glass surface boundary helps to characterize glass objects. Inspired by prior semantic segmentation approaches with challenging image types such as X-ray or CT scans, we propose separated internal-external boundary attention modules that individually learn and selectively integrate visual characteristics of the inside and outside region of glass surface from a single color image. Our proposed method is evaluated on six public benchmarks comparing with state-of-the-art methods showing promising results.