Balancing Efficiency and Quality: MoEISR for Arbitrary-Scale Image Super-Resolution
This work addresses efficiency issues in image super-resolution for applications requiring arbitrary scaling, though it is incremental as it builds on existing implicit function approaches.
The paper tackles the high computational cost of arbitrary-scale image super-resolution with implicit neural functions by introducing MoEISR, which reduces FLOPs significantly while maintaining or improving PSNR compared to existing methods.
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).