High Quality Segmentation for Ultra High-resolution Images

TL;DR

This paper introduces the Continuous Refinement Model (CRM), a novel approach for ultra high-resolution image segmentation that improves accuracy and efficiency by mimicking human-like coarse-to-fine object recognition.

Contribution

The paper proposes CRM, a new model that continuously refines features for ultra high-resolution image segmentation, demonstrating superior accuracy and generalization over existing methods.

Findings

CRM is fast and effective for ultra high-resolution segmentation.

CRM outperforms traditional methods in accuracy and computational efficiency.

The model generalizes well across different resolutions.

Abstract

To segment 4K or 6K ultra high-resolution images needs extra computation consideration in image segmentation. Common strategies, such as down-sampling, patch cropping, and cascade model, cannot address well the balance issue between accuracy and computation cost. Motivated by the fact that humans distinguish among objects continuously from coarse to precise levels, we propose the Continuous Refinement Model~(CRM) for the ultra high-resolution segmentation refinement task. CRM continuously aligns the feature map with the refinement target and aggregates features to reconstruct these images' details. Besides, our CRM shows its significant generalization ability to fill the resolution gap between low-resolution training images and ultra high-resolution testing ones. We present quantitative performance evaluation and visualization to show that our proposed method is fast and effective on image segmentation refinement. Code will be released at https://github.com/dvlab-research/Entity.