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

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Oh, Young Jae, Kim, Jihun, Nam, Jihoon, Kim, Tae Hyun
Natura: Preprint
Pubblicazione: 2023
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866918180712087552
author Oh, Young Jae
Kim, Jihun
Nam, Jihoon
Kim, Tae Hyun
author_facet Oh, Young Jae
Kim, Jihun
Nam, Jihoon
Kim, Tae Hyun
contents 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).
format Preprint
id arxiv_https___arxiv_org_abs_2311_12077
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Balancing Efficiency and Quality: MoEISR for Arbitrary-Scale Image Super-Resolution
Oh, Young Jae
Kim, Jihun
Nam, Jihoon
Kim, Tae Hyun
Computer Vision and Pattern Recognition
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).
title Balancing Efficiency and Quality: MoEISR for Arbitrary-Scale Image Super-Resolution
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2311.12077