SEP-YOLO: Fourier-Domain Feature Representation for Transparent Object Instance Segmentation
This work addresses a significant challenge in computer vision, particularly for applications that require accurate segmentation of transparent objects, such as robotics or autonomous vehicles.
The authors tackled the problem of transparent object instance segmentation, achieving state-of-the-art performance with their proposed SEP-YOLO framework. SEP-YOLO outperformed existing methods, which often fail due to the inherent properties of transparent objects.
Transparent object instance segmentation presents significant challenges in computer vision, due to the inherent properties of transparent objects, including boundary blur, low contrast, and high dependence on background context. Existing methods often fail as they depend on strong appearance cues and clear boundaries. To address these limitations, we propose SEP-YOLO, a novel framework that integrates a dual-domain collaborative mechanism for transparent object instance segmentation. Our method incorporates a Frequency Domain Detail Enhancement Module, which separates and enhances weak highfrequency boundary components via learnable complex weights. We further design a multi-scale spatial refinement stream, which consists of a Content-Aware Alignment Neck and a Multi-scale Gated Refinement Block, to ensure precise feature alignment and boundary localization in deep semantic features. We also provide high-quality instance-level annotations for the Trans10K dataset, filling the critical data gap in transparent object instance segmentation. Extensive experiments on the Trans10K and GVD datasets show that SEP-YOLO achieves state-of-the-art (SOTA) performance.