cs.CVNov 17, 2026

SandBAR: A Band-Asymmetric Architecture for Underwater Image Restoration with Removable Frequency Scaffolding

Authors: Yanzi Liu, Haoran Hou, Jiachi Tong, Shen Chen, Shuang Chen

Organizations: School of Biomedical Engineering & Imaging Sciences, King’s College London, London, UK · Institute of Psychiatry, Psychology & Neuroscience, King’s College London, London, UK · Department of Mathematics, Imperial College London, London, UK · Department of Computer Science, Durham University, Durham, UK

Abstract

Light scattering, absorption and turbidity degrade underwater imagery through complementary frequency tendencies: large-scale, channel-dependent appearance distortions and local high-frequency detail loss. This band asymmetry motivates different forms of restoration for global colour and local structure. Our primary contribution is SandBAR, a novel unified band-asymmetric architecture for underwater image restoration. Rather than treating frequency processing as an isolated module, SandBAR organises the restoration pipeline around band asymmetry at the block, encoder and objective levels. Within this architecture, we introduce a novel band-asymmetric sandwich block with a reserved post-attention repair slot and the Split-band Parallel Asymmetric Repair Kernel (SPARK), a novel module that applies channel-aware large-support correction to the low band, which predominantly carries large-scale appearance distortions, and lightweight local refinement to the detail-bearing high band, thereby restoring global colour while preserving fine structure. To deliver the global cast to the depth at which the network represents global structure, a learnable low-frequency guidance path injects a low-pass view of the input into the deep encoder, and a three-scale spatial-frequency objective supervises the same axis throughout the decoder. Building on the reserved post-attention slot, we further introduce Post-attention Scaffold Training (PaST), a novel removable nonlinear scaffolding scheme that trains the permanent SandBAR graph under band-specific capacity and runs it at inference without that capacity. SandBAR reaches 29.89 / 28.92 / 22.77 dB on EUVP / LSUI / UIEB and establishes a new three-domain mean state of the art on the benchmark family, exceeding the strongest published result by approximately 1.0 dB. PaST adds no parameters or FLOPs at inference and preserves matched latency.

Figures & tables

Explore similar work

CardsList
  1. Multi-level Constrained Learning for Underwater Image Enhancement

    Oct 29, 2026Wangtao Bao, Liping Xie, Kanjian Zhang +1Underwater Image EnhancementImage Restoration

  2. WaveFlow-UIE: A Single-Pipeline Wavelet-Domain Flow Model for Efficient Underwater Image Restoration

    Nov 11, 2026Abdulaziz Alfaraj, Mohammed Al Naser, Hassan Al Nasser +1Underwater Image EnhancementImage Restoration

  3. Degradation-Guided Underwater Image Restoration with Task-Oriented Latent Control

    Aug 9, 2026Xu Zhang, Xuhui Cao, Kangzhe Yuan +5Underwater Image EnhancementUnderwater Imaging