Implicit neural representation (INR) has become the standard approach for arbitrary-scale image super-resolution (ASSR). To date, no empirical study has systematically examined the effectiveness of existing methods, nor investigated the effects of different training recipes, such as scaling laws, objective design, and optimization strategies. A rigorous empirical analysis is essential not only for benchmarking performance and revealing true gains but also for establishing the current state of ASSR, identifying saturation limits, and highlighting promising directions. We fill this gap by comparing existing techniques across diverse settings and presenting aggregated performance results on multiple image quality metrics. We contribute a unified framework and code repository to facilitate reproducible comparisons. Furthermore, we investigate the impact of carefully controlled training configurations on perceptual image quality and examine a new loss function that penalizes intensity variations while preserving edges, textures, and finer details during training. We conclude the following key insights that have been previously overlooked: (1) Recent, more complex INR methods provide only marginal improvements over earlier methods. (2) Model performance is strongly correlated to training configurations, a factor overlooked in prior works. (3) The proposed loss enhances texture fidelity across architectures, emphasizing the role of objective design for targeted perceptual gains. (4) Scaling laws apply to INR-based ASSR, confirming predictable gains with increased model complexity and data diversity.

翻译：隐式神经表示（INR）已成为任意尺度图像超分辨率（ASSR）的标准方法。迄今为止，尚无实证研究系统性地检验现有方法的有效性，亦未深入探究不同训练方案（如缩放定律、目标函数设计及优化策略）的影响。严谨的实证分析不仅对基准性能评估和揭示真实增益至关重要，而且对确立当前ASSR的发展现状、识别性能饱和极限以及指明有前景的研究方向具有关键意义。我们通过比较不同设置下的现有技术，并在多个图像质量指标上呈现聚合性能结果，填补了这一空白。我们贡献了一个统一的框架与代码库，以促进可复现的比较研究。此外，我们探究了精细控制的训练配置对感知图像质量的影响，并研究了一种新的损失函数，该函数在训练过程中惩罚强度变化，同时保留边缘、纹理及精细细节。我们总结出以下先前被忽视的关键见解：（1）近期更复杂的INR方法相较于早期方法仅带来边际性能提升。（2）模型性能与训练配置高度相关，此因素在先前工作中被忽视。（3）所提出的损失函数能提升不同架构的纹理保真度，强调了目标函数设计对于实现针对性感知增益的作用。（4）缩放定律适用于基于INR的ASSR，证实了模型复杂度与数据多样性的增加可带来可预测的性能提升。