mlsanityData to 14 Oct 2026

Balancing Efficiency and Quality: MoEISR for Arbitrary-Scale Image Super-Resolution

arXiv 2311.12077 ↗First posted 20 Nov 2023cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

Arbitrary-scale image super-resolution employing implicit neural functions has gained significant attention lately due to its capability to upscale images across diverse scales utilizing only a single model. Nevertheless, these methodologies have imposed substantial computational demands as they involve querying every target pixel to a single resource-intensive decoder. In this paper, we introduce a novel and efficient framework, the Mixture-of-Experts Implicit Super-Resolution (MoEISR), which enables super-resolution at arbitrary scales with significantly increased computational efficiency without sacrificing reconstruction quality. MoEISR dynamically allocates the most suitable decoding expert to each pixel using a lightweight mapper module, allowing experts with varying capacities to reconstruct pixels across regions with diverse complexities. Our experiments demonstrate that MoEISR successfully reduces significant amount of floating point operations (FLOPs) while delivering comparable or superior peak signal-to-noise ratio (PSNR).

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 40 of its 47 references that are in the map. First posted on arXiv 20 Nov 2023.

Builds on

40 of 47 references.

References · 40

  1. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  2. 2017Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layercited by 3,509
  3. 2021Switch Transformers: Scaling to Trillion Parameter Models with Simple and Efficient Sparsitycited by 3,073
  4. 2016Categorical Reparameterization with Gumbel-Softmaxcited by 2,739
  5. 2021SwinIR: Image Restoration Using Swin Transformercited by 1,887
  6. 2017Enhanced Deep Residual Networks for Single Image Super-Resolutioncited by 1,552
  7. 2018Image Super-Resolution Using Very Deep Residual Channel Attention Networkscited by 1,264
  8. 2014Image Super-Resolution Using Deep Convolutional Networkscited by 1,224
  9. 2016Real-Time Single Image and Video Super-Resolution Using an Efficient Sub-Pixel Convolutional Neural Networkcited by 1,204
  10. 2016The Concrete Distribution: A Continuous Relaxation of Discrete Random Variablescited by 1,148
  11. 2018Learning Implicit Fields for Generative Shape Modelingcited by 1,060
  12. 2020Pre-Trained Image Processing Transformercited by 893
28 more
  1. 2019Scene Representation Networks: Continuous 3D-Structure-Aware Neural Scene Representationscited by 864
  2. 2018Residual Dense Network for Image Super-Resolutioncited by 799
  3. 2021Scaling Vision with Sparse Mixture of Expertscited by 747
  4. 2019Differentiable Volumetric Rendering: Learning Implicit 3D Representations without 3D Supervisioncited by 700
  5. 2021KiloNeRF: Speeding up Neural Radiance Fields with Thousands of Tiny MLPscited by 673
  6. 2020Learning Continuous Image Representation with Local Implicit Image Functioncited by 552
  7. 2022Activating More Pixels in Image Super-Resolution Transformercited by 438
  8. 2019SAL: Sign Agnostic Learning of Shapes from Raw Datacited by 390
  9. 2020Local Implicit Grid Representations for 3D Scenescited by 373
  10. 2019Texture Fields: Learning Texture Representations in Function Spacecited by 210
  11. 2022Multimodal Contrastive Learning with LIMoE: the Language-Image Mixture of Expertscited by 203
  12. 2019Meta-SR: A Magnification-Arbitrary Network for Super-Resolutioncited by 181
  13. 2019AdaShare: Learning What To Share For Efficient Deep Multi-Task Learningcited by 160
  14. 2020Adversarial Generation of Continuous Imagescited by 135
  15. 2021Local Texture Estimator for Implicit Representation Functioncited by 127
  16. 2019Spatio-Temporal Filter Adaptive Network for Video Deblurringcited by 106
  17. 2020Image Generators with Conditionally-Independent Pixel Synthesiscited by 106
  18. 2022VideoINR: Learning Video Implicit Neural Representation for Continuous Space-Time Super-Resolutioncited by 101
  19. 2021ClassSR: A General Framework to Accelerate Super-Resolution Networks by Data Characteristiccited by 81
  20. 2022CiaoSR: Continuous Implicit Attention-in-Attention Network for Arbitrary-Scale Image Super-Resolutioncited by 70
  21. 2020Learning A Single Network for Scale-Arbitrary Super-Resolutioncited by 66
  22. 2023Cascaded Local Implicit Transformer for Arbitrary-Scale Super-Resolutioncited by 52
  23. 2018Crafting a Toolchain for Image Restoration by Deep Reinforcement Learningcited by 47
  24. 2019Path-Restore: Learning Network Path Selection for Image Restorationcited by 40
  25. 2016RAISR: Rapid and Accurate Image Super Resolutioncited by 27
  26. 2021SRWarp: Generalized Image Super-Resolution under Arbitrary Transformationcited by 27
  27. 2022Adaptive Patch Exiting for Scalable Single Image Super-Resolutioncited by 16
  28. 2021Variational Multi-Task Learning with Gumbel-Softmax Priorscited by 15

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2024Arbitrary-Scale Image Generation and Upsampling using Latent Diffusion Model and Implicit Neural Decoder
  2. 2025Mixture of Ranks with Degradation-Aware Routing for One-Step Real-World Image Super-Resolution
  3. 2026SRGAN-CKAN: Expressive Super-Resolution with Nonlinear Functional Operators under Minimal Resources
  4. 2023Implicit Diffusion Models for Continuous Super-Resolution
  5. 2026Fast Image Super-Resolution via Consistency Rectified Flow
  6. 2025OmniScaleSR: Unleashing Scale-Controlled Diffusion Prior for Faithful and Realistic Arbitrary-Scale Image Super-Resolution
  7. 2024S3Mamba: Arbitrary-Scale Super-Resolution via Scaleable State Space Model
  8. 2026IQ-LUT: interpolated and quantized LUT for efficient image super-resolution