Pixel to Gaussian: Ultra-Fast Continuous Super-Resolution with 2D Gaussian Modeling
This addresses the need for efficient and high-quality arbitrary-scale super-resolution in image processing, representing an incremental improvement over existing implicit neural representation methods.
The paper tackles the problem of arbitrary-scale super-resolution by proposing a ContinuousSR framework with a Pixel-to-Gaussian paradigm, which reconstructs high-resolution images from low-resolution inputs using Gaussian Splatting, achieving rendering in just 1ms per scale.
Arbitrary-scale super-resolution (ASSR) aims to reconstruct high-resolution (HR) images from low-resolution (LR) inputs with arbitrary upsampling factors using a single model, addressing the limitations of traditional SR methods constrained to fixed-scale factors (\textit{e.g.}, $\times$ 2). Recent advances leveraging implicit neural representation (INR) have achieved great progress by modeling coordinate-to-pixel mappings. However, the efficiency of these methods may suffer from repeated upsampling and decoding, while their reconstruction fidelity and quality are constrained by the intrinsic representational limitations of coordinate-based functions. To address these challenges, we propose a novel ContinuousSR framework with a Pixel-to-Gaussian paradigm, which explicitly reconstructs 2D continuous HR signals from LR images using Gaussian Splatting. This approach eliminates the need for time-consuming upsampling and decoding, enabling extremely fast arbitrary-scale super-resolution. Once the Gaussian field is built in a single pass, ContinuousSR can perform arbitrary-scale rendering in just 1ms per scale. Our method introduces several key innovations. Through statistical ana