Research map / Image generation / Image restoration
The Devil Is in the Details: Window-Based Attention for Image Compression
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 window-based attention (WAM) (ablation) | Minnen2020 · Minnen2020, λ=0.0035 | PSNR: 30.32 -> 30.58 | Helped |
| Add window-based attention (WAM) (ablation) | Minnen2020 · Minnen2020, λ=0.0130 | PSNR: 33.87 -> 34.10 | Helped |
| Add NLAM instead of WAM (ablation) | Minnen2020 · Minnen2020, λ=0.0035 | PSNR: 30.32 -> 30.42 | Helped |
| Add NLAM instead of WAM (ablation) | Minnen2020 · Minnen2020, λ=0.0130 | PSNR: 33.87 -> 33.95 | Helped |
| Add window-based attention (WAM) (ablation) | Minnen2020 · Minnen2020, λ=0.0035 | bpp: 0.198 -> 0.199 | Hurt |
| Add window-based attention (WAM) (ablation) | Minnen2020 · Minnen2020, λ=0.0130 | bpp: 0.454 -> 0.448 | Helped |
| Add NLAM instead of WAM (ablation) | Minnen2020 · Minnen2020, λ=0.0035 | bpp: 0.198 -> 0.202 | Hurt |
| Add NLAM instead of WAM (ablation) | Minnen2020 · Minnen2020, λ=0.0130 | bpp: 0.454 -> 0.467 | Hurt |
Closest papers by meaning
- Bridging the Divide: Reconsidering Softmax and Linear Attention (NeurIPS 2024 · similarity 0.82)
- Test-Time Fine-Tuning of Image Compression Models for Multi-Task Adaptability (CVPR 2025 · similarity 0.81)
- PAROAttention: Pattern-Aware ReOrdering for Efficient Sparse and Quantized Attention in Visual Generation Models (NeurIPS 2025 · similarity 0.81)
- When MLLMs Meets Compression Distortion: A Coding Paradigm Tailored to MLLMs (ICLR 2026 · similarity 0.81)
- DiTFastAttn: Attention Compression for Diffusion Transformer Models (NeurIPS 2024 · similarity 0.81)
- Linear Attention Modeling for Learned Image Compression (CVPR 2025 · similarity 0.81)
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.