让轻量级神经体积表示自动预测误差分布，提升重建可靠性。
Error Aware Distribution Prediction for Lightweight Implicit Neural Representations
- 将回归训练转为分类任务，用分桶建模输出分布
- 在保持高重建质量的同时实现强误差感知能力
- 适合对精度和可靠性有要求的轻量化场景
隐式神经表示（INRs）能紧凑编码体数据，但作为有损近似器，不可避免存在预测误差。本文提出一种轻量级方法，通过不确定性估计工具，让INR同时预测相对误差规模并建模输出分布。传统不确定性估计依赖计算开销大或预设分布假设（如高斯分布）。本研究将基于回归的INR训练重构为分类任务，将连续目标离散化为多个区间，实现灵活的分布建模，可捕捉复杂的多模态行为。我们分析了回归与分类在INR训练中的权衡，结果表明，分类设置在重建质量上表现优异，且在不确定性估计方面具备竞争力，优于传统回归方法。
原文摘要 · Abstract (English)
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.
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。