High-Precision Dichotomous Image Segmentation via Probing Diffusion Capacity

TL;DR

This paper introduces DiffDIS, a diffusion-based high-resolution image segmentation model that leverages pre-trained diffusion models and auxiliary edge tasks to achieve fast, accurate, and detailed object segmentation.

Contribution

It proposes a novel diffusion-driven segmentation approach that reduces inference time and enhances boundary detail preservation using a task-specific denoising strategy and auxiliary edge generation.

Findings

Achieves state-of-the-art results on DIS5K dataset.

Demonstrates rapid inference while maintaining high segmentation accuracy.

Effectively preserves fine object boundaries in high-resolution images.

Abstract

In the realm of high-resolution (HR), fine-grained image segmentation, the primary challenge is balancing broad contextual awareness with the precision required for detailed object delineation, capturing intricate details and the finest edges of objects. Diffusion models, trained on vast datasets comprising billions of image-text pairs, such as SD V2.1, have revolutionized text-to-image synthesis by delivering exceptional quality, fine detail resolution, and strong contextual awareness, making them an attractive solution for high-resolution image segmentation. To this end, we propose DiffDIS, a diffusion-driven segmentation model that taps into the potential of the pre-trained U-Net within diffusion models, specifically designed for high-resolution, fine-grained object segmentation. By leveraging the robust generalization capabilities and rich, versatile image representation prior of the SD models, coupled with a task-specific stable one-step denoising approach, we significantly reduce the inference time while preserving high-fidelity, detailed generation. Additionally, we introduce an auxiliary edge generation task to not only enhance the preservation of fine details of the object boundaries, but reconcile the probabilistic nature of diffusion with the deterministic demands of segmentation. With these refined strategies in place, DiffDIS serves as a rapid object mask generation model, specifically optimized for generating detailed binary maps at high resolutions, while demonstrating impressive accuracy and swift processing. Experiments on the DIS5K dataset demonstrate the superiority of DiffDIS, achieving state-of-the-art results through a streamlined inference process. The source code will be publicly available at https://github.com/qianyu-dlut/DiffDIS.