对比6种隐式表示模型，发现复杂度提升对超分效果帮助有限。

Implicit neural representation (INR) has become the standard approach for arbitrary-scale image super-resolution (ASSR). However, no systematic empirical study has examined the effectiveness of existing methods under consistent conditions, nor investigated the effects of different training recipes, such as objective design, optimization strategies, and scaling behavior. 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 training 6 INR-based ASSR methods under 9 controlled training recipes and evaluating them across 7 datasets and 7 image quality assessment (IQA) metrics, presenting aggregated performance results through a unified ranking framework that enables more reliable interpretation of performance comparisons and evaluation claims. Furthermore, we investigate the impact of carefully controlled training configurations on perceptual image quality and analyze the role of auxiliary objectives in preserving edges, textures, and fine details during training. Our analysis yields the following insights, previously overlooked: (1) Recent, more complex INR methods provide only marginal improvements over earlier methods, indicating architectural saturation on existing benchmarks. (2) Model performance is strongly correlated with training configurations, a factor neglected in prior comparisons. (3) Auxiliary objectives consistently enhance texture fidelity across architectures compared to standard L1-Loss, emphasizing the role of objective design for targeted perceptual gains. (4) INR-based ASSR exhibits consistent, monotonic scaling behavior across model capacity, training compute, and data diversity, though with diminishing returns as complexity grows.