Research map / Image generation / Autoregressive and latent generation
Attention-Guided Hierarchical Structure Aggregation for Image Matting
Check your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 channel-wise attention to distill pyramidal features (ablation) | HAttMatting · Composition-1k test | SAD: 126.31 -> 96.67 | Helped |
| Add SSIM loss (ablation) | HAttMatting baseline · Composition-1k test | SAD: 126.31 -> 102.79 | Helped |
| Add low-level appearance cues (ablation) | HAttMatting baseline · Composition-1k test | SAD: 126.31 -> 89.39 | Helped |
| Add low-level appearance cues and channel-wise attention (ablation) | HAttMatting baseline · Composition-1k test | SAD: 126.31 -> 72.73 | Helped |
| Add low-level appearance cues and spatial attention (ablation) | HAttMatting baseline · Composition-1k test | SAD: 126.31 -> 54.91 | Helped |
| Add low-level appearance cues, channel-wise attention, and spatial attention (ablation) | HAttMatting baseline · Composition-1k test | SAD: 126.31 -> 49.67 | Helped |
| Add SSIM loss (ablation) | HAttMatting baseline · Distinctions-646 test | SAD: 129.94 -> 121.79 | Helped |
| Add low-level appearance cues (ablation) | HAttMatting baseline · Distinctions-646 test | SAD: 129.94 -> 98.88 | Helped |
| Add channel-wise attention (ablation) | HAttMatting baseline · Distinctions-646 test | SAD: 129.94 -> 104.23 | Helped |
| Add low-level appearance cues and channel-wise attention (ablation) | HAttMatting baseline · Distinctions-646 test | SAD: 129.94 -> 85.57 | Helped |
| Add low-level appearance cues and spatial attention (ablation) | HAttMatting baseline · Distinctions-646 test | SAD: 129.94 -> 78.14 | Helped |
| Add low-level appearance cues, channel-wise attention, and spatial attention (ablation) | HAttMatting baseline · Distinctions-646 test | SAD: 129.94 -> 57.31 | Helped |
Closest papers by meaning
- Image Matting without Matting-Specific Annotations via Eikonal Fields (NeurIPS 2026 · similarity 0.91)
- Revisiting Context Aggregation for Image Matting (ICML 2024 · similarity 0.90)
- Training Matting Models Without Alpha Labels (AAAI 2025 · similarity 0.90)
- In-Context Matting (CVPR 2024 · similarity 0.89)
- DRIP: Unleashing Diffusion Priors for Joint Foreground and Alpha Prediction in Image Matting (NeurIPS 2024 · similarity 0.88)
- Privileged Prior Information Distillation for Image Matting (AAAI 2024 · similarity 0.88)
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.