# Meticulous Object Segmentation

arXiv: https://arxiv.org/abs/2012.07181 · HTML: https://mlsanity.com/paper/2012.07181/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 13 Dec 2020.

## Built on by (most cited first, 8 of 8)

- [Highly Accurate Dichotomous Image Segmentation](https://mlsanity.com/paper/2203.03041/) (2022)
- [High Quality Segmentation for Ultra High-resolution Images](https://mlsanity.com/paper/2111.14482/) (2021)
- [Multi-view Aggregation Network for Dichotomous Image Segmentation](https://mlsanity.com/paper/2404.07445/) (2024)
- [DC-Net: Divide-and-Conquer for Salient Object Detection](https://mlsanity.com/paper/2305.14955/) (2023)
- [High-Precision Dichotomous Image Segmentation via Probing Diffusion Capacity](https://mlsanity.com/paper/2410.10105/) (2024)
- [TETRIS: Towards Exploring the Robustness of Interactive Segmentation](https://mlsanity.com/paper/2402.06132/) (2024)
- [A Robust Morphological Approach for Semantic Segmentation of Very High Resolution Images](https://mlsanity.com/paper/2208.01254/) (2022)
- [FlowDIS: Language-Guided Dichotomous Image Segmentation with Flow Matching](https://mlsanity.com/paper/2605.05077/) (2026)

## Abstract (arXiv)

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.