arXiv:2511.11015v1 Announce Type: new 
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.

يقدم المقال كتلة فك التشفير Selectively Suppressed Perfect Reconstruction (SUPER) ، المصممة لتحسين متغيرات U-Net المستخدمة في المشاكل العكسية. تتناول هذه الطريقة مشكلة فقدان المعلومات التي تحد من استعادة التفاصيل الدقيقة في الصور. من خلال الاستفادة من خاصية الاستعادة المثالية للموجات ، تقوم SUPER بقمع الميزات الزائدة بشكل انتقائي ، مما يحسن من ثراء التمثيل مع الحفاظ على الكفاءة الحسابية. تظهر التجارب فعاليتها عبر معايير متنوعة ، خاصة في تقسيم الشقوق الدقيقة ومهام إزالة الضوضاء من الصور.

El artículo presenta el bloque decodificador Selectively Suppressed Perfect Reconstruction (SUPER), diseñado para mejorar las variantes de U-Net utilizadas en problemas inversos. Este método aborda el problema de la pérdida de información que limita la recuperación de detalles finos en las imágenes. Al aprovechar la propiedad de reconstrucción perfecta de las wavelets, SUPER suprime selectivamente características redundantes, mejorando así la riqueza representacional y manteniendo la eficiencia computacional. Los experimentos demuestran su efectividad en diversos benchmarks, especialmente en l…

Cet article présente le bloc décodeur Selectively Suppressed Perfect Reconstruction (SUPER), conçu pour améliorer les variantes de U-Net utilisées dans les problèmes inverses. Cette méthode aborde le problème de la perte d'information qui limite la récupération des détails fins dans les images. En s'appuyant sur la propriété de reconstruction parfaite des ondelettes, SUPER supprime sélectivement les caractéristiques redondantes, améliorant ainsi la richesse représentationnelle tout en maintenant l'efficacité computationnelle. Des expériences démontrent son efficacité sur divers benchmarks, not…

The paper presents the Selectively Suppressed Perfect Reconstruction (SUPER) Decoder Block, designed to enhance U-Net variants used in inverse problems. This method addresses the issue of information loss that limits the recovery of fine details in images. By leveraging the perfect reconstruction property of wavelets, SUPER selectively suppresses redundant features, thus improving representational richness and maintaining computational efficiency. Experiments demonstrate its effectiveness across various benchmarks, particularly in thin-crack segmentation and image denoising tasks.

SUPER Decoder Block for Reconstruction-Aware U-Net Variants

Was this article worth reading? Share it

Ready to build your own newsroom?