通过输入输出的核变换提升隐式神经表示性能
Exploring Kernel Transformations for Implicit Neural Representations
- 在不改变模型结构前提下，研究输入输出的核变换影响
- 结合缩放与平移可显著提升隐式神经表示，计算开销极小
- 从深度和归一化角度解释缩放平移带来的性能增益
隐式神经表示（INRs）利用神经网络将坐标映射到对应属性以表示信号，广泛应用于图像表示中，以像素坐标为输入、像素值为输出。与以往关注模型内部组件（如激活函数）的研究不同，本文首次探索在保持模型不变的前提下，输入输出的核变换对性能的影响。研究发现，一种简单的缩放与平移组合方法能显著提升INR表现，且计算开销可忽略。同时，本文从深度和归一化两个视角解释了该变换带来的性能提升机制。本工作为未来通过核变换理解与改进隐式神经表示提供了新思路。
原文摘要 · Abstract (English)
Implicit neural representations (INRs), which leverage neural networks to represent signals by mapping coordinates to their corresponding attributes, have garnered significant attention. They are extensively utilized for image representation, with pixel coordinates as input and pixel values as output. In contrast to prior works focusing on investigating the effect of the model's inside components (activation function, for instance), this work pioneers the exploration of the effect of kernel transformation of input/output while keeping the model itself unchanged. A byproduct of our findings is a simple yet effective method that combines scale and shift to significantly boost INR with negligible computation overhead. Moreover, we present two perspectives, depth and normalization, to interpret the performance benefits caused by scale and shift transformation. Overall, our work provides a new avenue for future works to understand and improve INR through the lens of kernel transformation.
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。