A single autoencoder trained on 6,376 simulation volumes compresses unseen scientific volumes at 2,000–10,000× compression with higher reported fidelity than prior compressors, with adjustable rate at inference.
Fastneuralrepresentationsfor direct volume rendering.Comput
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.GR 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
EVOLVE: Efficient Learned Volume Compression with Variable-Rate Encoding on a Cross-Domain Database
A single autoencoder trained on 6,376 simulation volumes compresses unseen scientific volumes at 2,000–10,000× compression with higher reported fidelity than prior compressors, with adjustable rate at inference.