OPE-SR: Orthogonal Position Encoding for Designing a Parameter-free Upsampling Module in Arbitrary-scale Image Super-Resolution

TL;DR

This paper introduces OPE-Upscale, a parameter-free, efficient module using orthogonal position encoding for arbitrary-scale image super-resolution, achieving comparable results to state-of-the-art methods without training parameters.

Contribution

The paper proposes a novel orthogonal position encoding and a parameter-free upsampling module that replaces traditional INR-based methods for efficient arbitrary-scale image super-resolution.

Findings

OPE-Upscale achieves high efficiency and low memory usage.

The method produces comparable super-resolution quality to state-of-the-art.

OPE corresponds to a set of orthogonal basis, validating the design.

Abstract

Implicit neural representation (INR) is a popular approach for arbitrary-scale image super-resolution (SR), as a key component of INR, position encoding improves its representation ability. Motivated by position encoding, we propose orthogonal position encoding (OPE) - an extension of position encoding - and an OPE-Upscale module to replace the INR-based upsampling module for arbitrary-scale image super-resolution. Same as INR, our OPE-Upscale Module takes 2D coordinates and latent code as inputs; however it does not require training parameters. This parameter-free feature allows the OPE-Upscale Module to directly perform linear combination operations to reconstruct an image in a continuous manner, achieving an arbitrary-scale image reconstruction. As a concise SR framework, our method has high computing efficiency and consumes less memory comparing to the state-of-the-art (SOTA), which has been confirmed by extensive experiments and evaluations. In addition, our method has comparable results with SOTA in arbitrary scale image super-resolution. Last but not the least, we show that OPE corresponds to a set of orthogonal basis, justifying our design principle.