ECNR: Efficient Compressive Neural Representation of Time-Varying Volumetric Datasets

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 …

compression cs.cv cs.gr cs.lg current datasets encode global inference massive mlp neural compression paper perceptron practice representation simplicity training