Research map / Image generation / Image restoration
Deep Diversity-Enhanced Feature Representation of Hyperspectral Images
Jinhui Hou, Zhiyu Zhu, Junhui Hou, Hui Liu, Huanqiang Zeng, Deyu Meng
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 |
|---|---|---|---|
| replace 3-D conv with ReS3-ConvSet (ablation) | ReS3Net · ICVL denoising sigma=70 | MPSNR: 39.34 -> 39.85 | Improved |
| replace 3-D conv with ReS3-ConvSet (ablation) | ReS3Net · CAVE SR x4 | MPSNR: 40.98 -> 41.35 | Improved |
| replace 3-D conv with ReS3-ConvSet (ablation) | ReS3Net · Indian Pines classification | OA: 82.38 -> 87.84 | Improved |
| add DA-Reg regularizer (ablation) | ReS3Net · ICVL denoising sigma=70 | MPSNR: 39.85 -> 40.01 | Improved |
| add DA-Reg regularizer (ablation) | ReS3Net · CAVE SR x4 | MPSNR: 41.35 -> 41.44 | Improved |
| add DA-Reg regularizer (ablation) | ReS3Net · Indian Pines classification | OA: 87.84 -> 90.70 | Improved |
| add symmetry property to ReS3-ConvSet (ablation) | ReS3-ConvSet · ICVL denoising sigma=70 | MPSNR: 39.68 -> 39.85 | Improved |
| add symmetry property to ReS3-ConvSet (ablation) | ReS3-ConvSet · CAVE SR x4 | MPSNR: 41.20 -> 41.35 | Improved |
| raise rank upper bound from 3M to 9M (ablation) | ReS3-ConvSet · CAVE SR x4 | MPSNR: 41.35 -> 41.32 | No clear effect |
| use 1-D kernels instead of 2-D kernels at rank 3M (ablation) | ReS3-ConvSet · CAVE SR x4 | MPSNR: 41.28 -> 41.35 | Improved |
| increase kernel size from 3 to 7 for ReS3-ConvSet (ablation) | ReS3-ConvSet · CAVE SR x4 | MPSNR: 41.35 -> 41.48 | Improved |
| increase kernel size from 3 to 7 for 3-D conv (ablation) | 3-D conv · CAVE SR x4 | MPSNR: 40.98 -> 40.73 | Hurt |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- FreeNet — FReeNet: Multi-Identity Face Reenactment (CVPR 2020) · 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
- LESSViT: Robust Hyperspectral Representation Learning under Spectral Configuration Shift (NeurIPS 2026 · similarity 0.88)
- Hyperspectral Image Reconstruction Using a Deep Spatial-Spectral Prior (CVPR 2019 · similarity 0.87)
- Hyperspectral Image Reconstruction via Combinatorial Embedding of Cross-Channel Spatio-Spectral Clues (AAAI 2024 · similarity 0.87)
- Learning Tensor Low-Rank Prior for Hyperspectral Image Reconstruction (CVPR 2021 · similarity 0.86)
- Joint Camera Spectral Sensitivity Selection and Hyperspectral Image Recovery (ECCV 2018 · similarity 0.86)
- A Trainable Spectral-Spatial Sparse Coding Model for Hyperspectral Image Restoration (NeurIPS 2021 · similarity 0.86)
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.
