EVOLVE: Efficient Learned Volume Compression with Variable-Rate Encoding on a Cross-Domain Database

2026-07-20

AI Summary

This work addresses the challenge of compressing large-scale volumetric data from scientific simulations, where traditional methods struggle to preserve fine structures at high compression ratios and implicit neural representations suffer from high optimization costs and fixed compression rates. To overcome these limitations, the authors propose EVOLVE, an autoencoder-based framework for volumetric data compression. Key contributions include the construction of a cross-domain, large-scale dataset comprising 6,376 volumes, the design of macro- and micro-network architectures to enhance representational capacity, and the introduction of a learnable gain mechanism coupled with a three-stage training strategy that enables, for the first time, continuous and variable compression rates within a single model. Experiments demonstrate that EVOLVE significantly outperforms conventional compressors in reconstruction quality on multiple unseen scientific datasets and surpasses implicit neural representation methods by orders of magnitude in speed.

Abstract

Large-scale scientific simulations generate volumetric data at rates that far outpace advances in storage and network bandwidth, making effective lossy compression increasingly critical. However, conventional compressors often struggle to preserve fine structural details at high compression ratios (CRs), and implicit neural representations (INRs) require costly per-volume optimization and produce models with fixed CRs. To respond, we present EVOLVE, an autoencoder (AE)-based volume-compression framework that targets high CRs for offline compression, with three key contributions. First, we construct a large-scale cross-domain database of 6,376 volumes from 21 scientific simulations, curated via perceptual hashing to ensure diversity, enabling the optimized model to extract features that generalize across volumes within the covered scientific simulation domains. Second, we reexamine the design space of AE-based compressors and incorporate several macro- and micro-designs into a vanilla AE to develop EVOLVE, which substantially improves the expressive power and compression capability. Third, we develop a learnable gain mechanism with a three-stage training strategy to enable variable-rate encoding, allowing a single model to support continuous CR adjustment at inference time. Experiments on multiple unseen scientific simulation datasets demonstrate that EVOLVE achieves substantially higher CRs than conventional compressors at comparable reconstruction quality, while delivering compression speeds that are orders of magnitude faster than INR-based methods, highlighting its promise as a strong alternative for compressing scientific data. The code, model weights, and results are available on our project page at https://evolve-vis.github.io.

Problem

• volume compression
• scientific simulation
• lossy compression
• high compression ratio
• variable-rate encoding

Innovation

• variable-rate encoding
• cross-domain database
• autoencoder-based compression
• learnable gain mechanism
• scientific volume compression