ECNR: Efficient Compressive Neural Representation of Time-Varying Volumetric Datasets
This work addresses efficiency issues in neural compression for large volumetric data, offering a domain-specific incremental improvement.
The paper tackles the problem of slow training and inference in neural compression for time-varying volumetric datasets by introducing ECNR, which uses a Laplacian pyramid with multiple small MLPs for adaptive fitting and parallelization, achieving significant speed improvements compared to state-of-the-art methods like SZ3, TTHRESH, and neurcomp.
Due to its conceptual simplicity and generality, compressive neural representation has emerged as a promising alternative to traditional compression methods for managing massive volumetric datasets. The current practice of neural compression utilizes a single large multilayer perceptron (MLP) to encode the global volume, incurring slow training and inference. This paper presents an efficient compressive neural representation (ECNR) solution for time-varying data compression, utilizing the Laplacian pyramid for adaptive signal fitting. Following a multiscale structure, we leverage multiple small MLPs at each scale for fitting local content or residual blocks. By assigning similar blocks to the same MLP via size uniformization, we enable balanced parallelization among MLPs to significantly speed up training and inference. Working in concert with the multiscale structure, we tailor a deep compression strategy to compact the resulting model. We show the effectiveness of ECNR with multiple datasets and compare it with state-of-the-art compression methods (mainly SZ3, TTHRESH, and neurcomp). The results position ECNR as a promising solution for volumetric data compression.