Research map / Image generation / Super-resolution
LAPRAN: A Scalable Laplacian Pyramid Reconstructive Adversarial Network for Flexible Compressive Sensing Reconstruction
Kai XU, Zhikang Zhang, Fengbo Ren
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 |
|---|---|---|---|
| use progressive Laplacian-pyramid reconstruction instead of single-step generation (CSGM) | LAPRAN · Set5 (CR=5) | PSNR (dB): 27.31 -> 34.79 | Improved |
| use progressive Laplacian-pyramid reconstruction instead of single-step generation (CSGM) | LAPRAN · Set14 (CR=30) | PSNR (dB): 23.97 -> 27.09 | Improved |
| raise compression ratio from 5 to 30 | LAPRAN · MNIST | PSNR (dB): 38.46 -> 31.28 | Hurt |
| raise compression ratio from 5 to 30 | D-AMP · CIFAR10 | PSNR (dB): 41.35 -> 10.62 | Hurt |
| raise compression ratio from 5 to 30 | LAPRAN · Set5 | PSNR (dB): 34.79 -> 28.61 | Hurt |
| raise compression ratio from 5 to 30 | ReconNet · Set5 | PSNR (dB): 31.78 -> 25.60 | Hurt |
| use LAPRAN instead of ReconNet | LAPRAN · Set14 (CR=20) | PSNR (dB): 25.38 -> 28.39 | Improved |
| use LAPRAN instead of ReconNet | LAPRAN · runtime, 64x64 patch (CR=5) | runtime (s): 2.005e-3 -> 6.241e-3 | Hurt |
| use LAPRAN instead of CSGM | LAPRAN · runtime, 64x64 patch (CR=5) | runtime (s): 1.448e-1 -> 6.241e-3 | Improved |
| use LAPRAN instead of TVAL3 | LAPRAN · runtime, 64x64 patch (CR=5) | runtime (s): 1.858e1 -> 6.241e-3 | Improved |
| use LAPRAN instead of LDAMP | LAPRAN · CIFAR10 (CR=10) | SSIM: 0.899 -> 0.943 | Improved |
| initialize each stage with weights of previous stage (weight transfer) | LAPRAN · training | stability/convergence | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 0 of 1 on most shared results.
- ReconNet — ReconNet: Non-Iterative Reconstruction of Images From Compressively Sensed Measurements (CVPR 2016) · better on 0 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
- Deep Laplacian Pyramid Networks for Fast and Accurate Super-Resolution (CVPR 2017 · similarity 0.88)
- Deep Compressed Sensing (ICML 2019 · similarity 0.88)
- Measuring Robustness in Deep Learning Based Compressive Sensing (ICML 2021 · similarity 0.87)
- Reconstruction-free Cascaded Adaptive Compressive Sensing (CVPR 2024 · similarity 0.86)
- CPP-Net: Embracing Multi-Scale Feature Fusion into Deep Unfolding CP-PPA Network for Compressive Sensing (CVPR 2024 · similarity 0.86)
- Multi-Cross Sampling and Frequency-Division Reconstruction for Image Compressed Sensing (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.
