Year: 2025
Type: preprint
Abstract: Current approaches to dichotomous image segmentation (DIS) treat image matting and object segmentation as fundamentally different tasks. As improvements in image segmentation become increasingly challenging to achieve, combining image matting and grayscale segmentation techniques offers promising new directions for architectural innovation. Inspired by the possibility of aligning these two model tasks, we propose a new architectural approach for DIS called Confidence-Guided Matting (CGM). We created the first CGM model called Background Erase Network (BEN). BEN consists of two components: BEN Base for initial segmentation and BEN Refiner for confidence-based refinement. Our approach achieves substantial improvements over current state-of-the-art methods on the DIS5K validation dataset, demonstrating that matting-based refinement can significantly enhance segmentation quality. This work introduces a new paradigm for integrating matting and segmentation techniques, improving fine-grained object boundary prediction in computer vision.
Source: arXiv (Cornell University)
Authors: Meyer, Maxwell, Spruyt, Jack
Language: English
Subfield: Computer Vision and Pattern Recognition
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W6948314013
Cites:
Cited by:
Related to: