Meticulous Object Segmentation
This work addresses the problem of detailed object segmentation in high-resolution images, which is an incremental improvement for computer vision researchers and applications requiring precise object boundaries.
This paper introduces Meticulous Object Segmentation (MOS), a task for segmenting foreground objects with elaborate shapes in high-resolution images (2k-4k). They propose MeticulousNet, which uses a dedicated decoder with a Hierarchical Point-wise Refining block and a recursive coarse-to-fine refinement to achieve pixel-accurate segmentation boundaries, outperforming state-of-the-art methods.
Compared with common image segmentation tasks targeted at low-resolution images, higher resolution detailed image segmentation receives much less attention. In this paper, we propose and study a task named Meticulous Object Segmentation (MOS), which is focused on segmenting well-defined foreground objects with elaborate shapes in high resolution images (e.g. 2k - 4k). To this end, we propose the MeticulousNet which leverages a dedicated decoder to capture the object boundary details. Specifically, we design a Hierarchical Point-wise Refining (HierPR) block to better delineate object boundaries, and reformulate the decoding process as a recursive coarse to fine refinement of the object mask. To evaluate segmentation quality near object boundaries, we propose the Meticulosity Quality (MQ) score considering both the mask coverage and boundary precision. In addition, we collect a MOS benchmark dataset including 600 high quality images with complex objects. We provide comprehensive empirical evidence showing that MeticulousNet can reveal pixel-accurate segmentation boundaries and is superior to state-of-the-art methods for high resolution object segmentation tasks.