用单一全局带宽实现快速连续图像重建与超分，速度比基线快3倍以上。
GB-LSR: A Fast Local Spectral Image Representation with a Single Global Bandwidth for Continuous Reconstruction and Super-Resolution
- 固定网格分块，共享卷积特征预测傅里叶系数，仅用一个全局可训练带宽
- 在Kodak、Set14、Urban100上比同类方法高2.8-3.6dB PSNR，推理成本仅为四分之一
- 支持任意尺度超分，无角落平均加速1.77倍，内存降低35%且精度几乎不变
我们提出GB-LSR（全局带宽局部谱表示），一种用于连续图像重建的固定网格局部谱表示。图像域被划分为不重叠的方形块，每个块包含由共享卷积编码器特征预测的截断傅里叶基系数。所有块和图像共享一个可训练的全局标量带宽，任意连续坐标上的重建为固定大小基底收缩，计算开销与图像尺寸无关。研究了三种带宽处理方式：可训练全局标量（主方案）、固定全局标量、每块自适应带宽场。在Kodak、Set14、Urban100的标准原生重建基准上，主方案相比同预算的摊销式LIIF/LTE/WIRE复现版本提升2.8-3.6 dB PSNR和0.11-0.15 LPIPS，推理成本约为最慢基线的四分之一。实证表明单一全局标量已足够：每块自适应带宽在闭式局部性诊断或端到端消融中均未超越它。在独立的任意尺度超分辨率（ASR）扩展中，GB-LSR在标准超分协议下达到有竞争力的PSNR-Y，x4缩放下分别比LIIF-RDN快1.44倍、比LTE-SwinIR快3.25倍；同一扩展中，去除四个角局部集成平均的变体实现1.77倍加速，峰值内存降低35%，精度变化可忽略；同时将RDN编码器通道从64增至96，带来微小正向PSNR提升，加速1.58倍，峰值内存降低31%。原生重建结论限定于匹配预算摊销协议，超分结论限定于独立标准超分协议。
原文摘要 · Abstract (English)
We present GB-LSR (Global-Bandwidth Local Spectral Representation), a fixed-grid local spectral representation for continuous image reconstruction. The image domain is partitioned into non-overlapping square patches, each carrying coefficients for a truncated Fourier basis predicted from shared convolutional-encoder features. A single trainable scalar bandwidth is shared globally across all patches and images, and reconstruction at any continuous coordinate is a fixed-size basis contraction whose cost is independent of image size. We study three bandwidth-handling variants: a trainable global scalar (main), a fixed global scalar, and a per-patch bandwidth field. On a standardized native-reconstruction benchmark across Kodak, Set14, and Urban100, the main variant outperforms matched-budget amortized LIIF / LTE / WIRE re-implementations by 2.8-3.6 dB PSNR and 0.11-0.15 LPIPS, while running at roughly one-quarter of the slowest baseline's inference cost. The single global scalar suffices empirically: per-patch adaptive-bandwidth alternatives do not improve over it on either a closed-form locality diagnostic or an end-to-end ablation. In a separate arbitrary-scale super-resolution (ASR) extension, GB-LSR achieves competitive PSNR-Y under a canonical-style SR protocol and runs 1.44x faster than LIIF-RDN and 3.25x faster than LTE-SwinIR at x4; within the same extension, a variant trained and evaluated without 4-corner local-ensemble averaging gives a 1.77x speedup with 35% lower peak memory and negligible PSNR change, while additionally widening the RDN encoder from 64 to 96 channels gives a small positive PSNR shift with a 1.58x speedup and 31% lower peak memory. Native-reconstruction claims are scoped to the matched-budget amortized protocol, and ASR claims are scoped to a separate canonical-style SR protocol.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。