用超像素提升图像与多维数据的隐式表示效果
Superpixel-informed Implicit Neural Representation for Multi-Dimensional Data
- 以广义超像素代替像素作为基本单元，融合语义信息
- 通过注意力MLP与共享字典矩阵实现跨区域特征交互
- 在图像和气象数据上优于现有隐式神经表示方法
隐式神经表示（INRs）近年受到关注，用于多维数据恢复。但传统INRs仅通过多层感知机（MLP）将坐标映射为数值，忽略了数据内在语义信息。为此，本文提出一种新型超像素引导的隐式神经表示（S-INR）。具体而言，采用广义超像素而非像素作为多维数据（如图像、气象数据）的基本单元。首先将广义超像素坐标输入专属注意力增强的MLP，再与共享字典矩阵交互。S-INR中精心设计的模块使我们能巧妙利用超像素内部及跨超像素的语义信息。在多种应用上的大量实验验证了其相对于先进INR方法的有效性与优越性。
原文摘要 · Abstract (English)
Recently, implicit neural representations (INRs) have attracted increasing attention for multi-dimensional data recovery. However, INRs simply map coordinates via a multi-layer perception (MLP) to corresponding values, ignoring the inherent semantic information of the data. To leverage semantic priors from the data, we propose a novel Superpixel-informed INR (S-INR). Specifically, we suggest utilizing generalized superpixel instead of pixel as an alternative basic unit of INR for multi-dimensional data (e.g., images and weather data). The coordinates of generalized superpixels are first fed into exclusive attention-based MLPs, and then the intermediate results interact with a shared dictionary matrix. The elaborately designed modules in S-INR allow us to ingenuously exploit the semantic information within and across generalized superpixels. Extensive experiments on various applications validate the effectiveness and efficacy of our S-INR compared to state-of-the-art INR methods.
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。