IEEE VIS 2024 Content: KD-INR: Time-Varying Volumetric Data Compression via Knowledge Distillation-based Implicit Neural Representation

KD-INR: Time-Varying Volumetric Data Compression via Knowledge Distillation-based Implicit Neural Representation

Jun Han -

Hao Zheng -

Change Bi -

Screen-reader Accessible PDF

Room: Bayshore I

2024-10-16T12:30:00ZGMT-0600Change your timezone on the schedule page
2024-10-16T12:30:00Z
Exemplar figure, described by caption below
We propose KD-INR, a knowledge distillation-based implicit neural representation, enabling to sequentially compress time-varying data with memory effciency.
Fast forward
Keywords

Time-varying data compression, implicit neural representation, knowledge distillation, volume visualization.

Abstract

Traditional deep learning algorithms assume that all data is available during training, which presents challenges when handling large-scale time-varying data. To address this issue, we propose a data reduction pipeline called knowledge distillation-based implicit neural representation (KD-INR) for compressing large-scale time-varying data. The approach consists of two stages: spatial compression and model aggregation. In the first stage, each time step is compressed using an implicit neural representation with bottleneck layers and features of interest preservation-based sampling. In the second stage, we utilize an offline knowledge distillation algorithm to extract knowledge from the trained models and aggregate it into a single model. We evaluated our approach on a variety of time-varying volumetric data sets. Both quantitative and qualitative results, such as PSNR, LPIPS, and rendered images, demonstrate that KD-INR surpasses the state-of-the-art approaches, including learning-based (i.e., CoordNet, NeurComp, and SIREN) and lossy compression (i.e., SZ3, ZFP, and TTHRESH) methods, at various compression ratios ranging from hundreds to ten thousand.