SUPER Decoder Block for Reconstruction-Aware U-Net Variants

2025-11-14

AI Summary

U-Net variants often suffer from insufficient high-frequency detail recovery in inverse problem solving due to information bottlenecks introduced by skip connections. To address this, we propose the Reconstruction-Aware SUPER decoding block—the first to embed a fully reconstructive wavelet mechanism into the U-Net decoding path. By parameterizing wavelet filters and selectively suppressing redundant features, it enhances representational richness and detail fidelity without increasing computational overhead. The module is plug-and-play and architecture-agnostic, seamlessly integrating with diverse U-Net variants. On the CrackVision12K dataset, it achieves significant mIoU improvement for fine crack segmentation (<4 pixels). In the SIDD denoising benchmark, it delivers consistent PSNR gains. These results validate its capability for joint high- and low-frequency modeling and demonstrate strong cross-task generalization.

Technology Category

• Computer Vision: Segmentation
• Machine Learning: Deep Generative Models & Autoencoders
• Cognitive Modeling & Cognitive Systems: Neural Spike Coding

Application Category

• Graph Algorithms and Modeling for the Web: Representation, reconstruction, and subgraph or motif discovery in Web-related graphs
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Web Mining and Content Analysis: Large pretrained models with web data

Abstract

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.

Problem

• Addresses information loss in U-Net architectures for inverse problems
• Enhances recovery of fine high-frequency details in image reconstruction
• Provides plug-and-play decoder to eliminate reconstruction bottlenecks

Innovation

• SUPER decoder block prevents information loss
• Exploits wavelet perfect reconstruction property
• Plug-and-play solution for U-Net variants