无损 INR：无损体隐式神经表示
Lossless-INR: Lossless Volumetric Implicit Neural Representations
浏览论文内容
中文总结 AI 辅助
研究针对体数据的无损 INR 框架，核心方法是基于位平面分解，将重建转为逐位二进制分类，结合八叉树块分区与三元特征网格网络，实现零误码率和逐位精确重建，利于逼真渲染与下游分析。
中文摘要 AI 辅助
隐式神经表示（INR）方法提供连续的坐标到值的映射，并与直接体绘制自然集成，使其对表示体数据具有吸引力。然而，现有的基于 INR 的体数据方法本质上是有损的，即使是小的重建误差也会在渲染和下游分析中传播。在这项工作中，我们探索了 Lossless-INR，这是一个基于位平面分解的用于 3D 科学体数据的无损 INR 框架。通过将每个体素值分解为二进制位平面，我们将重建重新表述为逐位二进制分类，从而精确恢复简化为正确预测每个位。为了在保持表示紧凑的同时使这种优化易于处理，我们结合了一种八叉树块分区策略，该策略自适应地细分复杂区域，以及一个三元特征网格网络，其网格条目由一组三元值参数化。在各种体数据集上的实验表明，这种设计可以实现零误码率和逐位精确重建，从而能够以紧凑的表示进行逼真的渲染和下游分析。代码可在这个 https URL 上获取。
英文摘要
Implicit neural representation (INR) methods provide continuous coordinate-to-value mappings and integrate naturally with direct volume rendering, making them attractive for representing volumetric data. However, existing INR-based approaches for volumetric data are inherently lossy, and even small reconstruction errors can propagate through rendering and downstream analysis. In this work, we explore Lossless-INR, a lossless INR framework for 3D scientific volumetric data based on bit-plane decomposition. By decomposing each voxel value into binary bit-planes, we reformulate reconstruction as per-bit binary classification, so that exact recovery reduces to predicting every bit correctly. To make this optimization tractable while keeping the representation compact, we combine an octree block-partitioning strategy that adaptively subdivides complex regions with a ternary feature-grid network whose grid entries are parameterized by a ternary set of values. Experiments on diverse volumetric datasets show that this design can achieve zero bit-error rate and bit-exact reconstruction, enabling faithful rendering and downstream analysis with a compact representation. The code is available at https://github.com/TouKaienn/Lossless-INR.
发表机构
- University of Notre Dame（圣母大学）
机构由 AI 辅助整理，请以论文原文为准。
