# High-Precision Dichotomous Image Segmentation via Probing Diffusion Capacity arXiv: https://arxiv.org/abs/2410.10105 ยท HTML: https://mlsanity.com/paper/2410.10105/ ## Key facts - Cited by 7 papers in the map (data through 14 Oct 2026). - Placed in Medical imaging and segmentation, one of 14 directions in Diffusion models. - Builds on 38 of its 53 references that are in the map. - First posted on arXiv 14 Oct 2024. ## Placed in - Diffusion models / [Medical imaging and segmentation](https://mlsanity.com/diffusion/medical-imaging-and-segmentation/) ## Builds on (most cited first, 30 of 38) - [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020) - [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021) - [Adding Conditional Control to Text-to-Image Diffusion Models](https://mlsanity.com/paper/2302.05543/) (2023) - [CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Features](https://mlsanity.com/paper/1905.04899/) (2019) - [Latent Consistency Models: Synthesizing High-Resolution Images with Few-Step Inference](https://mlsanity.com/paper/2310.04378/) (2023) - [Adversarial Diffusion Distillation](https://mlsanity.com/paper/2311.17042/) (2023) - [Wonder3D: Single Image to 3D using Cross-Domain Diffusion](https://mlsanity.com/paper/2310.15008/) (2023) - [Structure-measure: A New Way to Evaluate Foreground Maps](https://mlsanity.com/paper/1708.00786/) (2017) - [Enhanced-alignment Measure for Binary Foreground Map Evaluation](https://mlsanity.com/paper/1805.10421/) (2018) - [Repurposing Diffusion-Based Image Generators for Monocular Depth Estimation](https://mlsanity.com/paper/2312.02145/) (2023) - [GeoWizard: Unleashing the Diffusion Priors for 3D Geometry Estimation from a Single Image](https://mlsanity.com/paper/2403.12013/) (2024) - [SegDiff: Image Segmentation with Diffusion Probabilistic Models](https://mlsanity.com/paper/2112.00390/) (2021) - [Anabranch Network for Camouflaged Object Segmentation](https://mlsanity.com/paper/2105.09451/) (2021) - [Multi-scale Interactive Network for Salient Object Detection](https://mlsanity.com/paper/2007.09062/) (2020) - [DDP: Diffusion Model for Dense Visual Prediction](https://mlsanity.com/paper/2303.17559/) (2023) - [Zoom In and Out: A Mixed-scale Triplet Network for Camouflaged Object Detection](https://mlsanity.com/paper/2203.02688/) (2022) - [Suppress and Balance: A Simple Gated Network for Salient Object Detection](https://mlsanity.com/paper/2007.08074/) (2020) - [One-Step Image Translation with Text-to-Image Models](https://mlsanity.com/paper/2403.12036/) (2024) - [Bilateral Reference for High-Resolution Dichotomous Image Segmentation](https://mlsanity.com/paper/2401.03407/) (2024) - [Highly Accurate Dichotomous Image Segmentation](https://mlsanity.com/paper/2203.03041/) (2022) - [Boundary-preserving Mask R-CNN](https://mlsanity.com/paper/2007.08921/) (2020) - [Pyramid Grafting Network for One-Stage High Resolution Saliency Detection](https://mlsanity.com/paper/2204.05041/) (2022) - [ZoomNeXt: A Unified Collaborative Pyramid Network for Camouflaged Object Detection](https://mlsanity.com/paper/2310.20208/) (2023) - [Boundary-Aware Segmentation Network for Mobile and Web Applications](https://mlsanity.com/paper/2101.04704/) (2021) - [Revisiting Image Pyramid Structure for High Resolution Salient Object Detection](https://mlsanity.com/paper/2209.09475/) (2022) - [DiffusionEdge: Diffusion Probabilistic Model for Crisp Edge Detection](https://mlsanity.com/paper/2401.02032/) (2024) - [Learning Implicit Feature Alignment Function for Semantic Segmentation](https://mlsanity.com/paper/2206.08655/) (2022) - [Multi-view Aggregation Network for Dichotomous Image Segmentation](https://mlsanity.com/paper/2404.07445/) (2024) - [BetterDepth: Plug-and-Play Diffusion Refiner for Zero-Shot Monocular Depth Estimation](https://mlsanity.com/paper/2407.17952/) (2024) - [DFormer: Diffusion-guided Transformer for Universal Image Segmentation](https://mlsanity.com/paper/2306.03437/) (2023) ## Built on by (most cited first, 7 of 7) - [Image Generators are Generalist Vision Learners](https://mlsanity.com/paper/2604.20329/) (2026) - [BEN: Using Confidence-Guided Matting for Dichotomous Image Segmentation](https://mlsanity.com/paper/2501.06230/) (2025) - [SDMatte: Grafting Diffusion Models for Interactive Matting](https://mlsanity.com/paper/2508.00443/) (2025) - [High-Precision Dichotomous Image Segmentation via Depth Integrity-Prior and Fine-Grained Patch Strategy](https://mlsanity.com/paper/2503.06100/) (2025) - [LawDIS: Language-Window-based Controllable Dichotomous Image Segmentation](https://mlsanity.com/paper/2508.01152/) (2025) - [Toward Real-World High-Precision Image Matting and Segmentation](https://mlsanity.com/paper/2601.12080/) (2026) - [FlowDIS: Language-Guided Dichotomous Image Segmentation with Flow Matching](https://mlsanity.com/paper/2605.05077/) (2026) ## Abstract (arXiv) 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.