LawDIS: Language-Window-based Controllable Dichotomous Image Segmentation

TL;DR

LawDIS is a novel image segmentation framework that uses language prompts and window controls within a diffusion model to produce high-quality, customizable object masks, outperforming existing methods.

Contribution

It introduces a dual-mode controllable segmentation approach combining language-based and window-based refinement within a diffusion model, enabling personalized and precise mask generation.

Findings

Outperforms 11 state-of-the-art methods on DIS5K benchmark.

Achieves 4.6% higher Fβω score with combined control strategies.

Demonstrates high accuracy and personalization in object segmentation.

Abstract

We present LawDIS, a language-window-based controllable dichotomous image segmentation (DIS) framework that produces high-quality object masks. Our framework recasts DIS as an image-conditioned mask generation task within a latent diffusion model, enabling seamless integration of user controls. LawDIS is enhanced with macro-to-micro control modes. Specifically, in macro mode, we introduce a language-controlled segmentation strategy (LS) to generate an initial mask based on user-provided language prompts. In micro mode, a window-controlled refinement strategy (WR) allows flexible refinement of user-defined regions (i.e., size-adjustable windows) within the initial mask. Coordinated by a mode switcher, these modes can operate independently or jointly, making the framework well-suited for high-accuracy, personalised applications. Extensive experiments on the DIS5K benchmark reveal that our LawDIS significantly outperforms 11 cutting-edge methods across all metrics. Notably, compared to the second-best model MVANet, we achieve $F_\beta^\omega$ gains of 4.6\% with both the LS and WR strategies and 3.6\% gains with only the LS strategy on DIS-TE. Codes will be made available at https://github.com/XinyuYanTJU/LawDIS.