提出无损3D体数据隐式表示，实现精确重建与高效存储。
Lossless-INR: Lossless Volumetric Implicit Neural Representations
- 通过比特平面分解，将重建转为逐比特分类任务。
- 在多个数据集上实现零比特错误率和比特级精确恢复。
- 适合需要高保真重建的科学计算与可视化场景。
隐式神经表示（INR）通过连续坐标到值的映射，天然契合直接体渲染，适用于体数据建模。然而，现有基于INR的体数据方法本质上是有损的，微小的重建误差会传播至渲染和下游分析。本文提出Lossless-INR，一种基于比特平面分解的无损3D科学体数据隐式表示框架。通过将每个体素值分解为二进制比特平面，将重建问题重构为逐比特二分类任务，使精确恢复等价于所有比特正确预测。为使优化可行并保持表示紧凑，结合自适应分块的八叉树结构与三值特征网格网络（网格单元由三值参数化）。在多种体数据集上的实验表明，该设计可实现零比特错误率与比特级精确重建，支持无失真渲染与下游分析，且表示紧凑。代码已开源：https://github.com/TouKaienn/Lossless-INR。
原文摘要 · Abstract (English)
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.
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。