首个跨领域隐式神经表示基准，系统评测模型在多任务中的表现
INR-Bench: A Unified Benchmark for Implicit Neural Representations in Multi-Domain Regression and Reconstruction
- 基于NTK理论分析架构、编码方式对信号频率响应的影响
- 覆盖56种坐标MLP与22种坐标KAN，在9个任务上验证性能差异
- 适合研究隐式神经表示的算法设计者和评估者参考
隐式神经表示（INRs）因其连续性和无限分辨率优势，在多种信号处理任务中取得成功，但其有效性与局限性仍不明确。本文借助神经正切核（NTK）理论，分析了模型架构（经典MLP与新兴KAN）、位置编码及非线性基函数对不同频率信号响应的影响。基于此，提出首个专为多模态INR任务设计的综合基准INR-Bench，包含56种坐标MLP变体（4类位置编码、14种激活函数）和22种坐标KAN模型（采用不同基函数），在9个隐式多模态任务上进行评估。这些任务涵盖前向与反向问题，有效揭示不同模型的优劣，为未来研究奠定坚实基础。代码与数据集已开源：https://github.com/lif314/INR-Bench。
原文摘要 · Abstract (English)
Implicit Neural Representations (INRs) have gained success in various signal processing tasks due to their advantages of continuity and infinite resolution. However, the factors influencing their effectiveness and limitations remain underexplored. To better understand these factors, we leverage insights from Neural Tangent Kernel (NTK) theory to analyze how model architectures (classic MLP and emerging KAN), positional encoding, and nonlinear primitives affect the response to signals of varying frequencies. Building on this analysis, we introduce INR-Bench, the first comprehensive benchmark specifically designed for multimodal INR tasks. It includes 56 variants of Coordinate-MLP models (featuring 4 types of positional encoding and 14 activation functions) and 22 Coordinate-KAN models with distinct basis functions, evaluated across 9 implicit multimodal tasks. These tasks cover both forward and inverse problems, offering a robust platform to highlight the strengths and limitations of different neural models, thereby establishing a solid foundation for future research. The code and dataset are available at https://github.com/lif314/INR-Bench.
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。