发表机构
Vanderbilt University; University of Arizona（范德堡大学; 亚利桑那大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
研究针对隐式神经表示的预测误差问题，提出轻量级方法，将基于回归的INR训练转为分类任务，通过离散连续目标为bins实现灵活分布建模，经分析权衡表明该方法能通过不确定性估计获高重建质量和误差感知。
AI 中文摘要
隐式神经表示（INRs）能对体积进行紧凑编码，但作为有损逼近器不可避免存在预测误差。我们考虑通过使用不确定性估计工具预测分布来同时编码相对误差尺度的INRs。通常不确定性估计依赖计算昂贵的方法或关于预测分布的预定义参数假设。本研究提出一种轻量级方法，通过将连续目标离散化为 bins 将基于回归的 INR 训练重新表述为分类任务，实现灵活分布建模以捕获复杂多模态行为。我们分析了 INR 训练中回归与分类的权衡，证明与基于回归的方法相比，分类设置通过不确定性估计往往能实现高重建质量和有竞争力的误差感知。
英文摘要
Implicit neural representations (INRs) offer compact encoding of volumes, but as lossy approximators, inevitably have prediction errors. We consider INRs that can simultaneously encode relative error scales by predicting distributions using tools from uncertainty estimation. Typically, uncertainty estimation relies on computationally expensive approaches or on predefined parametric assumptions about the predictive distribution (e.g., Gaussian). In this study, we propose a lightweight method that reformulates regression-based INR training as a classification task by discretizing continuous targets into bins, enabling flexible distribution modeling to capture complex multimodal behaviors. We analyze the trade-off between regression and classification for INR training and demonstrate that the classification setting tends to achieve high reconstruction quality and competitive error awareness through uncertainty estimation, compared to regression-based approaches.
