paper-with-me

Papers

Efficient Model Agnostic Approach for Implicit Neural Representation Based Arbitrary-Scale Image Super-Resolution

2023-11-20 · Young Jae Oh, Jihun Kim, Tae Hyun Kim

Single image super-resolution (SISR) has experienced significant advancements, primarily driven by deep convolutional networks. Traditional networks, however, are limited to upscaling images to a fixed scale, leading to the utilization of implicit neural functions for generating arbitrarily scaled images. 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 up to 73% in floating point operations (FLOPs) while delivering comparable or superior peak signal-to-noise ratio (PSNR).

📄 PDF Abstract BibTeX arXiv:2311.12077

Code (0)

등록된 구현이 없습니다.

Tasks

Computational EfficiencyDecoderImage Super-ResolutionMixture-of-ExpertsSuper-Resolution

Similar Papers 제목 키워드 기반

Dynamic Implicit Image Function for Efficient Arbitrary-Scale Image Representation

2023-06-21 · Zongyao He, Zhi Jin

Recent years have witnessed the remarkable success of implicit neural representation methods. The recent work Local Implicit Image Function (LIIF) has achieved satisfactory performance for continuous image representation…

Computational EfficiencySuper-Resolution

Hyperspectral Image Fusion with Spectral-Band and Fusion-Scale Agnosticism

2026-02-02 · Yu-Jie Liang, Zihan Cao, Liang-Jian Deng, Yang Yang 외 arxiv

Current deep learning models for Multispectral and Hyperspectral Image Fusion (MS/HS fusion) are typically designed for fixed spectral bands and spatial scales, which limits their transferability across diverse sensors. …

Enhancing Multi-Scale Implicit Learning in Image Super-Resolution with Integrated Positional Encoding

2021-12-10 · Ying-Tian Liu, Yuan-Chen Guo, Song-Hai Zhang

Is the center position fully capable of representing a pixel? There is nothing wrong to represent pixels with their centers in a discrete image representation, but it makes more sense to consider each pixel as the aggreg…

Image Super-ResolutionSuper-Resolution

Cascaded Local Implicit Transformer for Arbitrary-Scale Super-Resolution

2023-03-29 · CVPR 2023 1 · Hao-Wei Chen, Yu-Syuan Xu, Min-Fong Hong, Yi-Min Tsai 외

Implicit neural representation has recently shown a promising ability in representing images with arbitrary resolutions. In this paper, we present a Local Implicit Transformer (LIT), which integrates the attention mechan…

Super-Resolution

Learning Dual-Level Deformable Implicit Representation for Real-World Scale Arbitrary Super-Resolution

2024-03-16 · Zhiheng Li, Muheng Li, Jixuan Fan, Lei Chen 외

Scale arbitrary super-resolution based on implicit image function gains increasing popularity since it can better represent the visual world in a continuous manner. However, existing scale arbitrary works are trained and…

Super-Resolution