Research map / Architectures and efficiency / Attention and transformers
Wavelength-Embedding-guided Filter-Array Transformer for Spectral Demosaicing
Haijin Zeng, Hiep Luong, Wilfried Philips
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 wavelength embedding to spectral attention (ablation) | WeFAT · ARAD validation | PSNR: 46.92 -> 47.87 | Improved |
| add MSFA attention (MaM) alone (ablation) | WeFAT · ARAD validation | PSNR: 46.92 -> 47.02 | Improved |
| combine wavelength embedding with MSFA attention (ablation) | WeFAT · ARAD validation | PSNR: 46.92 -> 48.03 | Improved |
| use MaM instead of bilinear interpolation or mosaic convolution for MSFA usage (ablation) | WeFAT · ARAD validation | PSNR: 42.88 / 43.22 -> 47.02 | Improved |
| add wavelength embedding and MSFA attention for cross-camera generalization | WeFAT · KAIST (10 scenes, trained on ARAD) | PSNR: 36.04 (InNet) -> 43.63 | Improved |
| use channel-wise spectral tokens with linear-cost attention instead of 3D CNN | WeFAT-M versus InNet · ARAD validation | FLOPs (G): 1430.63 -> 14.03 | Improved |
Closest papers by meaning
- Hybrid Spectral Denoising Transformer with Guided Attention (ICCV 2023 · similarity 0.88)
- CARL: Camera-Agnostic Representation Learning for Spectral Image Analysis (ICLR 2026 · similarity 0.88)
- Spatial-Spectral Transformer for Hyperspectral Image Denoising (AAAI 2023 · similarity 0.86)
- LESSViT: Robust Hyperspectral Representation Learning under Spectral Configuration Shift (NeurIPS 2026 · similarity 0.85)
- SPECAT: SPatial-spEctral Cumulative-Attention Transformer for High-Resolution Hyperspectral Image Reconstruction (CVPR 2024 · similarity 0.85)
- Hyperspectral Image Reconstruction via Combinatorial Embedding of Cross-Channel Spatio-Spectral Clues (AAAI 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.
