Saved in:
| Main Authors: | , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2511.11015 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866915617926283264 |
|---|---|
| author | Joo, Siheon Kim, Hongjo |
| author_facet | Joo, Siheon Kim, Hongjo |
| contents | Skip-connected encoder-decoder architectures (U-Net variants) are widely adopted for inverse problems but still suffer from information loss, limiting recovery of fine high-frequency details. We present Selectively Suppressed Perfect Reconstruction (SUPER), which exploits the perfect reconstruction (PR) property of wavelets to prevent information degradation while selectively suppressing (SS) redundant features. Free from rigid framelet constraints, SUPER serves as a plug-and-play decoder block for diverse U-Net variants, eliminating their intrinsic reconstruction bottlenecks and enhancing representational richness. Experiments across diverse crack benchmarks, including state-of-the-art (SOTA) models, demonstrate the structural potential of the proposed SUPER Decoder Block. Maintaining comparable computational cost, SUPER enriches representational diversity through increased parameterization. In small-scale in-domain experiments on the CrackVision12K dataset, SUPER markedly improves thin-crack segmentation performance, particularly for cracks narrower than 4 px, underscoring its advantage in high-frequency dominant settings. In smartphone image denoising on SIDD, where low-frequency components prevail, SUPER still achieves a moderate gain in PSNR, confirming its robustness across low- and high-frequency regimes. These results validate its plug-and-play generality across U-Net variants, achieving high-frequency fidelity and global coherence within a unified, reconstruction-aware framework. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2511_11015 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | SUPER Decoder Block for Reconstruction-Aware U-Net Variants Joo, Siheon Kim, Hongjo Computer Vision and Pattern Recognition Skip-connected encoder-decoder architectures (U-Net variants) are widely adopted for inverse problems but still suffer from information loss, limiting recovery of fine high-frequency details. We present Selectively Suppressed Perfect Reconstruction (SUPER), which exploits the perfect reconstruction (PR) property of wavelets to prevent information degradation while selectively suppressing (SS) redundant features. Free from rigid framelet constraints, SUPER serves as a plug-and-play decoder block for diverse U-Net variants, eliminating their intrinsic reconstruction bottlenecks and enhancing representational richness. Experiments across diverse crack benchmarks, including state-of-the-art (SOTA) models, demonstrate the structural potential of the proposed SUPER Decoder Block. Maintaining comparable computational cost, SUPER enriches representational diversity through increased parameterization. In small-scale in-domain experiments on the CrackVision12K dataset, SUPER markedly improves thin-crack segmentation performance, particularly for cracks narrower than 4 px, underscoring its advantage in high-frequency dominant settings. In smartphone image denoising on SIDD, where low-frequency components prevail, SUPER still achieves a moderate gain in PSNR, confirming its robustness across low- and high-frequency regimes. These results validate its plug-and-play generality across U-Net variants, achieving high-frequency fidelity and global coherence within a unified, reconstruction-aware framework. |
| title | SUPER Decoder Block for Reconstruction-Aware U-Net Variants |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2511.11015 |