神经残差建模用于保证误差界下的科学数据压缩
Neural Residual Modeling for Scientific Data Compression under Guaranteed Error Bounds
- University of Florida（佛罗里达大学）
机构由 AI 辅助整理，请以论文原文为准。
AI总结：
针对科学数据压缩，提出结合潜空间RVQ、U-Net像素空间残差校正和GAE误差界保证的后处理流水线，在S3D、JHTDB和E3SM数据集上提升压缩比并维持严格误差界。
AI中文摘要：
科学模拟数据的无损压缩越来越依赖于学习型潜空间架构，如残差向量量化（RVQ），它通过迭代量化基础表示及其残差来逐步降低重建误差。尽管有效，RVQ完全在潜空间中进行这种残差建模，使得重建的像素空间误差结构在很大程度上未被处理。在这项工作中，我们提出了一种后处理流水线，通过一个训练好的U-Net来增强基于RVQ的压缩器，该U-Net用于预测并校正原始体数据与其RVQ重建之间的像素空间残差。我们表明，这些残差在空间上具有结构性，而非由局部强度或梯度特征驱动，这证明了需要深度空间模型而非简单统计校正的必要性。U-Net校正后的重建随后通过一个保证自编码器（GAE）阶段，该阶段将剩余残差投影到逐块的PCA基上，以强制执行用户指定的逐块误差界。据我们所知，这是首个将潜空间RVQ、通过深度空间后处理网络进行的显式像素空间残差校正以及基于GAE的误差界保证结合在单一框架中用于科学数据压缩的流水线。我们在S3D、JHTDB和E3SM数据集上评估了我们的方法，展示了在NRMSE、压缩比方面相对于仅RVQ和标准残差校正基线的持续改进，同时保持了科学数据保真度所需的严格误差保证。
英文摘要：
Lossy compression of scientific simulation data increasingly relies on learned, latent-space architectures such as Residual Vector Quantization (RVQ), which iteratively quantize a base representation and its residuals to progressively reduce reconstruction error. While effective, RVQ performs this residual modeling entirely in latent space, leaving the pixel-space error structure of the reconstruction largely unaddressed. In this work, we propose a post-processing pipeline that augments an RVQ-based compressor with a U-Net trained to predict and correct pixel-space residuals between the original volume and its RVQ reconstruction. We show that these residuals are spatially structured rather than driven by local intensity or gradient features, motivating the need for a deep spatial model rather than simple statistical correction. The U-Net-corrected reconstruction is then passed through a Guaranteed Autoencoder (GAE) stage, which projects the remaining residual onto a per-block PCA basis to enforce a user-specified block-wise error bound. To the best of our knowledge, this is the first pipeline to combine latent-space RVQ, explicit pixel-space residual correction via a deep spatial post-processing network, and GAE-based error-bound guarantees within a single framework for scientific data compression. We evaluate our approach on S3D, JHTDB and E3SM datasets, demonstrating consistent improvements in NRMSE, compression ratio] over RVQ-only and standard residual-correction baselines, while maintaining strict error guarantees required for scientific data fidelity.
