EVOLVE: Efficient Learned Volume Compression with Variable-Rate Encoding on a Cross-Domain Database
Authors
Kaiyuan Tang (University of Notre Dame), Maizhe Yang (University of Notre Dame), Chaoli Wang (University of Notre Dame)
Presentation
- Session
- That's way too big!
- Time
- Thursday, Nov 12, 16:00 – 16:12 (US/Eastern) · session 15:00 – 16:30
- Location
- Hall America center
Links
Sign in to access the preprint PDF.
Sign in- Download Supplemental Material
Keywords
Volume compression, learning-based compressor, autoencoder, context model, database
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.
For Practitioners
Practitioners who work with large-scale scientific simulation data, including computational scientists, HPC engineers, scientific visualization developers, and research software engineers, would benefit from this work. EVOLVE enables much higher compression ratios than existing methods while maintaining high reconstruction quality, reducing storage and data transfer costs for large volumetric datasets. Its single-model variable-rate encoding also allows practitioners to flexibly adjust the compression ratio for different storage and bandwidth requirements without retraining separate models, making it suitable for offline archival and data distribution workflows.