A Frequency‐Decomposed Residual Learning Framework for Volume Data Neural Representation
Abstract Implicit neural representations (INRs) have been widely adopted for volume data modeling in scientific visualization due to their continuous representation capability and flexibility. However, existing INR‐based methods still struggle to accurately capture high‐frequency details due to spectral bias, which can degrade reconstruction quality and affect downstream analysis. To address this issue, we propose a frequency‐decomposed residual learning framework for neural volume representation. Specifically, we decompose the volume data into low‐frequency components and high‐frequency residuals, and jointly model them with a shared INR by reformulating volume representation as a multi‐task learning (MTL) problem. To alleviate potential learning conflicts between different frequency branches while preserving model compactness, we introduce a lightweight feature gating mechanism on top of the shared backbone to adaptively reweight shared features for the two branches, enabling more effective modeling of low‐ and high‐frequency information. Experimental results on multiple scientific datasets demonstrate that our method consistently outperforms existing approaches in reconstruction, super‐resolution, and compression tasks, while maintaining comparable model size and computational efficiency. Further ablation studies validate the effectiveness of the proposed frequency‐decomposition and feature gating mechanism. Source code is publicly available at https://github.com/LiuLan2001/FDNR .
Authors
- Huijie Zhang (ORCID: https://orcid.org/0000-0001-8006-4845)
- Weiyang Liu (ORCID: https://orcid.org/0000-0002-8234-3263)
- Yiming Lin (ORCID: https://orcid.org/0009-0004-4131-2147)
- Zhaohan Lv (ORCID: https://orcid.org/0009-0009-9961-7871)
Institutions
- Northeast Normal University (CN)
Publication Details
- Journal
- Computer Graphics Forum
- Published
- 2026-11-13
- DOI
- https://doi.org/10.1111/cgf.70618
- Primary Topic
- 3D Shape Modeling and Analysis
- Type
- article
- Field-Weighted Citation Impact
- 0.00
Funders
- National Natural Science Foundation of China