arXiv：cs.LG· Max Shad, Naeem Khoshnevis·· 5 小时前AI 评分33
GB-LSR：用可学习全局带宽做局部频谱解码的任意尺度超分辨率
GB-LSR: Local Spectral Decoding with a Learned Global Bandwidth for Arbitrary-Scale Super-Resolution
AI 导读
GB-LSR 提出一种固定网格局部频谱表示，用单个可训练标量带宽替代固定频谱截断，实现连续坐标图像解码。其超分版本 GB-LSR-Scalar-ASR 在 x4 下比 LIIF-RDN 快 1.25 倍，与 SRNO-RDN 速度相当，而后者在 Urban100 上峰值内存高出 15 倍。
正文
Abstract:We present GB-LSR (Global-Bandwidth Local Spectral Representation), a fixed-grid local spectral representation for continuous image decoding. The image domain is partitioned into non-overlapping square patches. Each patch carries coefficients for a truncated Fourier basis, predicted by a single linear projection from shared convolutional-encoder features, and one trainable scalar bandwidth is shared across every patch and every image. As in earlier local spectral decoders, decoding at a continuous coordinate is a fixed-size basis contraction whose cost is set by the spectral cutoff; GB-LSR learns the bandwidth of that basis instead of fixing it. We evaluate an arbitrary-scale super-resolution extension, GB-LSR-Scalar-ASR, against the authors' released LIIF, LTE, and SRNO checkpoints on the same RDN encoder, with every method scored under one protocol and timed in one session per scale, each on one GPU. It runs 1.25x faster than LIIF-RDN at x4 and as fast as SRNO-RDN, whose released code uses 15 times as much peak memory on Urban100. It trails the three encoder-matched baselines by 0.07 to 0.79 dB PSNR-Y in distribution, SRNO-RDN by 0.35 dB on average. Removing the local ensemble raises the speedup to 2.41x over LIIF-RDN and 1.95x over SRNO-RDN at x4, and to 3.00x and 2.41x at x8, without changing PSNR-Y beyond seed variation, at the cost of value jumps at cell boundaries of 0.22 gray levels (of 255) on average at x4. Against the EDSR-baseline checkpoints of five recent methods at x4, GB-LSR-Scalar-ASR scores above or within 0.17 dB on PSNR-Y of LMF, SRNO-EDSR, and OPE-SR-EDSR (1.39 to 6.43 million parameters against 22.02) and 0.14 to 0.57 dB below GSASR and Thera (20.44 and 5.85 million), and has a higher mean LPIPS at x4 than every baseline.
| Comments: | 28 pages, 11 figures, 16 tables; v2: substantially revised and retitled; the main evaluation is now arbitrary-scale super-resolution against released checkpoints, and the native-reconstruction experiments are a design study of GB-LSR variants |
| Subjects: | Computer Vision and Pattern Recognition (cs.CV); Graphics (cs.GR); Machine Learning (cs.LG) |
| Cite as: | arXiv:2606.19617 [cs.CV] |
| (or arXiv:2606.19617v2 [cs.CV] for this version) | |
| https://doi.org/10.48550/arXiv.2606.19617 arXiv-issued DOI via DataCite |
Submission history
From: Max Shad [view email]
[v1]
Wed, 17 Jun 2026 21:50:05 UTC (1,851 KB)
[v2]
Fri, 2 Oct 2026 07:10:25 UTC (2,115 KB)
来源：arXiv：cs.LG · arxiv.org