用傅里叶特征和动态采样实现无层级体积压缩，提速超60%且质量损失小。
Accelerated Volumetric Compression without Hierarchies: A Fourier Feature Based Implicit Neural Representation Approach
- 通过傅里叶特征编码与选择性体素采样，无需层级结构直接压缩体积数据。
- 训练时间减少63.7%（30→11分钟），PSNR仅降0.59dB，SSIM降0.008。
- 仅存网络权重，压缩率达14，适合医疗、仿真等需高效存储的应用。
体积数据压缩在医学成像、科学模拟和娱乐领域至关重要。本文提出一种无结构的神经压缩方法，结合傅里叶特征编码与选择性体素采样，生成紧凑的体积表示并加速收敛。动态体素选择采用形态学膨胀优先处理活跃区域，避免冗余计算且无需任何层级元数据。实验显示，稀疏训练使训练时间从30分钟降至11分钟，减少63.7%，仅导致轻微质量下降：PSNR从32.60 dB降至32.01 dB（-0.59 dB），SSIM从0.948降至0.940（-0.008）。最终的神经表示仅以网络权重形式存储，压缩率达14，消除传统数据加载开销。该方法将基于坐标的神经表示与高效体积压缩相结合，为实际应用提供可扩展的无层级解决方案。
原文摘要 · Abstract (English)
Volumetric data compression is critical in fields like medical imaging, scientific simulation, and entertainment. We introduce a structure-free neural compression method combining Fourierfeature encoding with selective voxel sampling, yielding compact volumetric representations and faster convergence. Our dynamic voxel selection uses morphological dilation to prioritize active regions, reducing redundant computation without any hierarchical metadata. In the experiment, sparse training reduced training time by 63.7 % (from 30 to 11 minutes) with only minor quality loss: PSNR dropped 0.59 dB (from 32.60 to 32.01) and SSIM by 0.008 (from 0.948 to 0.940). The resulting neural representation, stored solely as network weights, achieves a compression rate of 14 and eliminates traditional data-loading overhead. This connects coordinate-based neural representation with efficient volumetric compression, offering a scalable, structure-free solution for practical applications.
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。