Deep Learning based Super-Resolution for Medical Volume Visualization with Direct Volume Rendering
This work addresses the need for efficient high-quality rendering in medical visualization, but it is incremental as it applies existing super-resolution methods to a specific domain.
The paper tackles the problem of high computational cost in high-resolution medical volume rendering by proposing a deep learning-based super-resolution technique that upscales low-resolution frames to high resolution, achieving improved temporal stability with temporal reprojection.
Modern-day display systems demand high-quality rendering. However, rendering at higher resolution requires a large number of data samples and is computationally expensive. Recent advances in deep learning-based image and video super-resolution techniques motivate us to investigate such networks for high-fidelity upscaling of frames rendered at a lower resolution to a higher resolution. While our work focuses on super-resolution of medical volume visualization performed with direct volume rendering, it is also applicable for volume visualization with other rendering techniques. We propose a learning-based technique where our proposed system uses color information along with other supplementary features gathered from our volume renderer to learn efficient upscaling of a low-resolution rendering to a higher-resolution space. Furthermore, to improve temporal stability, we also implement the temporal reprojection technique for accumulating history samples in volumetric rendering.