Fourier Boundary Features Network with Wider Catchers for Glass Segmentation

TL;DR

This paper introduces FBWC, a novel neural network architecture that improves glass segmentation by effectively capturing boundary details and reducing false positives through Fourier-based and wide shallow branches.

Contribution

The paper presents a new network with wide shallow branches, Fourier convolution control, and attention mechanisms for enhanced glass boundary segmentation.

Findings

Outperforms state-of-the-art methods on three public datasets.

Effectively captures fine boundary details in glass images.

Reduces false positives caused by reflection noise.

Abstract

Glass largely blurs the boundary between the real world and the reflection. The special transmittance and reflectance quality have confused the semantic tasks related to machine vision. Therefore, how to clear the boundary built by glass, and avoid over-capturing features as false positive information in deep structure, matters for constraining the segmentation of reflection surface and penetrating glass. We proposed the Fourier Boundary Features Network with Wider Catchers (FBWC), which might be the first attempt to utilize sufficiently wide horizontal shallow branches without vertical deepening for guiding the fine granularity segmentation boundary through primary glass semantic information. Specifically, we designed the Wider Coarse-Catchers (WCC) for anchoring large area segmentation and reducing excessive extraction from a structural perspective. We embed fine-grained features by Cross Transpose Attention (CTA), which is introduced to avoid the incomplete area within the boundary caused by reflection noise. For excavating glass features and balancing high-low layers context, a learnable Fourier Convolution Controller (FCC) is proposed to regulate information integration robustly. The proposed method has been validated on three different public glass segmentation datasets. Experimental results reveal that the proposed method yields better segmentation performance compared with the state-of-the-art (SOTA) methods in glass image segmentation.