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

ECNR advocates MINER, a multiscale approach [31] proposed for implicit neural representation (INR) of image and point cloud Due to its conceptual simplicity and generality, compressive neural data. Similar to MINER, ECNR adaptively decomposes the spatiotemporal representation has emerged as a promising alternative to traditional volume into blocks via the Laplacian pyramid, starting compression methods for managing massive volumetric datasets. As such, a block is only partitioned further The current practice of neural compression utilizes a single large if its residual remains significant, demanding the capture of finer multilayer perceptron (MLP) to encode the global volume, incurring space-time details for accurate signal reconstruction. To fit the local slow training and inference. This paper presents an efficient compressive spatiotemporal blocks at each scale, we utilize multiple small neural representation (ECNR) solution for time-varying data MLPs, permitting fast encoding and decoding, reduced memory compression, utilizing the Laplacian pyramid for adaptive signal consumption, and enhanced reconstruction quality. Following a multiscale structure, we leverage multiple small Different from MINER, ECNR handles 4D (3D+time) volumetric MLPs at each scale for fitting local content or residual blocks. By datasets, while MINER only processes 2D static images or 3D mesh. Working in concert with the multiscale we group similar blocks into clusters, and each cluster consists of structure, we tailor a deep compression strategy to compact the nearly the same number of blocks. We then assign each cluster resulting model. We show the effectiveness of ECNR with multiple to an MLP and effectively train them in parallel. Furthermore, datasets and compare it with state-of-the-art compression methods we leverage a deep compression strategy (including block-guided (mainly SZ3, TTHRESH, and neurcomp).