Pixel to Gaussian: Ultra-Fast Continuous Super-Resolution with 2D Gaussian Modeling

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

@article{peng2025_2503.06617,
  title={ Pixel to Gaussian: Ultra-Fast Continuous Super-Resolution with 2D Gaussian Modeling },
  author={ Long Peng and Anran Wu and Wenbo Li and Peizhe Xia and Xueyuan Dai and Xinjie Zhang and Xin Di and Haoze Sun and Renjing Pei and Yang Wang and Yang Cao and Zheng-Jun Zha },
  journal={arXiv preprint arXiv:2503.06617},
  year={ 2025 }
}