Research map / Detection and segmentation / CNN features
High-Precision Dichotomous Image Segmentation via Depth Integrity-Prior and Fine-Grained Patch Strategy
Xianjie Liu, Keren Fu, Qijun Zhao
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| add pseudo-depth input via DAM-v2 (ablation) | PDFNet baseline · DIS-VD | F_beta^max: .841 -> .872 | Improved |
| add FSE module (ablation) | PDFNet baseline · DIS-VD | F_beta^max: .841 -> .885 | Improved |
| add integrity map S and boundary scores Bd to FSE (ablation) | PDFNet without depth · DIS-VD | F_beta^max: .885 -> .903 | Improved |
| add depth on top of FSE, S and Bd (ablation) | PDFNet · DIS-VD | F_beta^max: .903 -> .907 | Improved |
| add depth integrity-prior loss (ablation) | PDFNet · DIS-VD | F_beta^max: .907 -> .912 | Improved |
| add depth refinement SILog loss only (ablation) | PDFNet · DIS-VD | F_beta^max: .907 -> .909 | Improved |
| combine SILog depth refinement with integrity-prior loss (ablation) | PDFNet · DIS-VD | F_beta^max: .912 -> .915 | Improved |
| add integrity-prior loss to other RGB-D models (ablation) | MAGNet · DIS-VD | F_beta^max: .867 -> .870 | Improved |
| add integrity-prior loss to other RGB-D models (ablation) | CPNet · DIS-VD | F_beta^max: .892 -> .895 | Improved |
| increase patch count from 1x1 to 8x8 (ablation) | PDFNet · DIS-VD | F_beta^max: .907 -> .915 | Improved |
| increase patch count from 8x8 to 16x16 (ablation) | PDFNet · DIS-VD | F_beta^max: .915 -> .910 | Hurt |
| increase MVANet patches beyond 2x2 (ablation) | MVANet · DIS-VD | F_beta^max: .904 -> .803 (3x3) | Hurt |
Closest papers by meaning
- Multi-view Aggregation Network for Dichotomous Image Segmentation (CVPR 2024 · similarity 0.88)
- High-Precision Dichotomous Image Segmentation via Probing Diffusion Capacity (ICLR 2025 · similarity 0.88)
- PDDM: Pseudo Depth Diffusion Model for RGB-PD Semantic Segmentation Based in Complex Indoor Scenes (AAAI 2025 · similarity 0.86)
- Zero-shot Depth Completion via Test-time Alignment with Affine-invariant Depth Prior (AAAI 2025 · similarity 0.85)
- MaskFactory: Towards High-quality Synthetic Data Generation for Dichotomous Image Segmentation (NeurIPS 2024 · similarity 0.85)
- DiffCut: Catalyzing Zero-Shot Semantic Segmentation with Diffusion Features and Recursive Normalized Cut (NeurIPS 2024 · similarity 0.85)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
