# GB-LSR: Local Spectral Decoding with a Learned Global Bandwidth for Arbitrary-Scale Super-Resolution

arXiv: https://arxiv.org/abs/2606.19617 · HTML: https://mlsanity.com/paper/2606.19617/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 22 of its 35 references that are in the map.
- First posted on arXiv 17 Jun 2026.

## Builds on (most cited first, 22 of 22)

- [The Unreasonable Effectiveness of Deep Features as a Perceptual Metric](https://mlsanity.com/paper/1801.03924/) (2018)
- [Implicit Neural Representations with Periodic Activation Functions](https://mlsanity.com/paper/2006.09661/) (2020)
- [Fourier Features Let Networks Learn High Frequency Functions in Low Dimensional Domains](https://mlsanity.com/paper/2006.10739/) (2020)
- [SwinIR: Image Restoration Using Swin Transformer](https://mlsanity.com/paper/2108.10257/) (2021)
- [Enhanced Deep Residual Networks for Single Image Super-Resolution](https://mlsanity.com/paper/1707.02921/) (2017)
- [Image Super-Resolution Using Very Deep Residual Channel Attention Networks](https://mlsanity.com/paper/1807.02758/) (2018)
- [Pre-Trained Image Processing Transformer](https://mlsanity.com/paper/2012.00364/) (2020)
- [Residual Dense Network for Image Super-Resolution](https://mlsanity.com/paper/1802.08797/) (2018)
- [Learning Continuous Image Representation with Local Implicit Image Function](https://mlsanity.com/paper/2012.09161/) (2020)
- [WIRE: Wavelet Implicit Neural Representations](https://mlsanity.com/paper/2301.05187/) (2023)
- [Meta-SR: A Magnification-Arbitrary Network for Super-Resolution](https://mlsanity.com/paper/1903.00875/) (2019)
- [Local Texture Estimator for Implicit Representation Function](https://mlsanity.com/paper/2111.08918/) (2021)
- [CiaoSR: Continuous Implicit Attention-in-Attention Network for Arbitrary-Scale Image Super-Resolution](https://mlsanity.com/paper/2212.04362/) (2022)
- [Cascaded Local Implicit Transformer for Arbitrary-Scale Super-Resolution](https://mlsanity.com/paper/2303.16513/) (2023)
- [Super-Resolution Neural Operator](https://mlsanity.com/paper/2303.02584/) (2023)
- [Latent Modulated Function for Computational Optimal Continuous Image Representation](https://mlsanity.com/paper/2404.16451/) (2024)
- [Generalized and Efficient 2D Gaussian Splatting for Arbitrary-scale Super-Resolution](https://mlsanity.com/paper/2501.06838/) (2025)
- [OPE-SR: Orthogonal Position Encoding for Designing a Parameter-free Upsampling Module in Arbitrary-scale Image Super-Resolution](https://mlsanity.com/paper/2303.01091/) (2023)
- [HIIF: Hierarchical Encoding based Implicit Image Function for Continuous Super-resolution](https://mlsanity.com/paper/2412.03748/) (2024)
- [Adaptive Local Implicit Image Function for Arbitrary-scale Super-resolution](https://mlsanity.com/paper/2208.04318/) (2022)
- [Thera: Aliasing-Free Arbitrary-Scale Super-Resolution with Neural Heat Fields](https://mlsanity.com/paper/2311.17643/) (2023)
- [Local Implicit Wavelet Transformer for Arbitrary-Scale Super-Resolution](https://mlsanity.com/paper/2411.06442/) (2024)

## Abstract (arXiv)

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.