Research map / Image generation / Image restoration
AnyBand-Diff: A Unified Remote Sensing Image Generation and Band Repair Framework with Spectral Priors
Zhao zuopeng, Ying Liu, xiaoyu Li, Su Luo, Lu Li, Wenwen Liu
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 MCD (ablation) | AnyBand-Diff · Arbitrary multiband (3 bands) | PSNR (dB): 33.18 -> 34.25 | Improved |
| add PGS (ablation) | AnyBand-Diff · Arbitrary multiband (3 bands) | PSNR (dB): 32.10 -> 34.25 | Improved |
| add MSPL (ablation) | AnyBand-Diff · Arbitrary multiband (3 bands) | PSNR (dB): 31.45 -> 34.25 | Improved |
| add MCD and PGS (ablation) | AnyBand-Diff · Arbitrary multiband (3 bands) | PSNR (dB): 30.12 -> 34.25 | Improved |
| add all modules (ablation) | AnyBand-Diff · Arbitrary multiband (3 bands) | PSNR (dB): 28.75 -> 34.25 | Improved |
| raise PGS guidance scale from 0 to 1.0 (ablation) | AnyBand-Diff · PaviaU 50% masking | PSNR (dB): 27.68 -> 29.65 | Improved |
| raise PGS guidance scale from 1.0 to 2.0 (ablation) | AnyBand-Diff · PaviaU 50% masking | PSNR (dB): 29.65 -> 28.91 | Hurt |
| add PGS and MSPL | SSDiff · 50% band masking | PSNR (dB): 24.02 -> 26.03 | Improved |
| add PGS and MSPL | CRS-Diff · 50% band masking | PSNR (dB): 24.12 -> 26.21 | Improved |
| add PGS (guidance gradient at inference) (ablation) | AnyBand-Diff · Efficiency | latency (ms/img): 1350 -> 1420 | Hurt |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 4 of 4 on most shared results.
- HSI-Gene — HSIGene: A Foundation Model for Hyperspectral Image Generation (TPAMI 2025) · better on 9 of 9 shared results
- DiffusionSat — DiffusionSat: A Generative Foundation Model for Satellite Imagery (ICLR 2024) · better on 1 of 1 shared result
- SSDiff — SSDiff: Spatial-spectral Integrated Diffusion Model for Remote Sensing Pansharpening (NeurIPS 2024) · better on 1 of 1 shared result
- ControlNet — ControlNet++: Improving Conditional Controls with Efficient Consistency Feedback (ECCV 2024) · better on 1 of 1 shared result
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- DiffSCI: Zero-Shot Snapshot Compressive Imaging via Iterative Spectral Diffusion Model (CVPR 2024 · similarity 0.89)
- Building Bridges across Spatial and Temporal Resolutions: Reference-Based Super-Resolution via Change Priors and Conditional Diffusion Model (CVPR 2024 · similarity 0.88)
- SSDiff: Spatial-spectral Integrated Diffusion Model for Remote Sensing Pansharpening (NeurIPS 2024 · similarity 0.87)
- Spectral Progressive Diffusion for Efficient Image and Video Generation (NeurIPS 2026 · similarity 0.86)
- BUFF: Bayesian Uncertainty Guided Diffusion Probabilistic Model for Single Image Super-Resolution (AAAI 2025 · similarity 0.85)
- Unmixing Diffusion for Self-Supervised Hyperspectral Image Denoising (CVPR 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.
