用二维高斯点云实现任意倍率超分辨率，1毫秒内完成渲染。
Pixel to Gaussian: Ultra-Fast Continuous Super-Resolution with 2D Gaussian Modeling
- 将像素映射为2D高斯点云，直接构建连续图像信号。
- 单次构建后任意缩放仅需1毫秒，速度提升显著。
- 适合需要实时超分的场景，如视频流处理或交互式应用。
任意倍率超分辨率（ASSR）旨在使用单一模型从低分辨率（LR）输入重建任意放大倍数的高分辨率（HR）图像，克服传统超分辨率方法仅支持固定倍率（如×2）的局限性。近期基于隐式神经表示（INR）的方法通过建模坐标到像素的映射取得进展，但其效率受限于重复上采样与解码过程，且重建质量受坐标函数固有表征能力的制约。为此，我们提出一种新型连续超分框架ContinuousSR，采用像素到高斯的范式，利用高斯溅射显式重建2D连续的高分辨率信号。该方法无需耗时的上采样和解码步骤，实现极快的任意倍率超分辨率。一旦高斯场在单次遍历中构建完成，即可在每种尺度下仅用1毫秒完成渲染。本方法引入多项关键创新，包括统计分析、高斯优化策略及高效的渲染机制，显著提升了速度与重建质量。
原文摘要 · Abstract (English)
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
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。