期刊
IEEE TRANSACTIONS ON VISUALIZATION AND COMPUTER GRAPHICS
卷 29, 期 12, 页码 4951-4963出版社
IEEE COMPUTER SOC
DOI: 10.1109/TVCG.2022.3197203
关键词
Task analysis; Data visualization; Rendering (computer graphics); Deep learning; Superresolution; Neural networks; Decoding; Volume visualization; implicit neural representation; data generation; visualization generation
CoordNet is a coordinate-based framework that tackles various tasks related to time-varying volumetric data visualization without modifying the network architecture. The method achieves this by decomposing the inputs and outputs into a unified representation and learning a function from coordinates to values. Experimental results show that CoordNet outperforms state-of-the-art approaches in data generation and visualization tasks.
Although deep learning has demonstrated its capability in solving diverse scientific visualization problems, it still lacks generalization power across different tasks. To address this challenge, we propose CoordNet, a single coordinate-based framework that tackles various tasks relevant to time-varying volumetric data visualization without modifying the network architecture. The core idea of our approach is to decompose diverse task inputs and outputs into a unified representation (i.e., coordinates and values) and learn a function from coordinates to their corresponding values. We achieve this goal using a residual block-based implicit neural representation architecture with periodic activation functions. We evaluate CoordNet on data generation (i.e., temporal super-resolution and spatial super-resolution) and visualization generation (i.e., view synthesis and ambient occlusion prediction) tasks using time-varying volumetric data sets of various characteristics. The experimental results indicate that CoordNet achieves better quantitative and qualitative results than the state-of-the-art approaches across all the evaluated tasks. Source code and pre-trained models are available at https://github.com/stevenhan1991/CoordNet.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据