FovDots: Foveated rendering dataset
收藏www.repository.cam.ac.uk2025-01-21 收录
下载链接：
https://www.repository.cam.ac.uk/items/946f4ec7-ce9e-45fa-bf2d-ae298d5daa06
下载链接
链接失效反馈官方服务：
资源简介：
FovDots is a video quality dataset that contains simulated artifacts that are typical for foveated rendering methods. The video sequences contain moving dots (disks) of different luminance. The foveated rendering is simulated by sampling pixels more sparsely at large eccentricities, reconstructing missing pixels with an in-painting method, and then using a filter to reduce aliasing artifacts.
The dataset was used to calibrate and test FovVideoVDP: A visible difference predictor for wide field-of-view video.
The details of the dataset can be found in the paper:
Mantiuk, Rafał K., Gyorgy Denes, Alexandre Chapiro, Anton Kaplanyan, Gizem Rufo, Romain Bachy, Trisha Lian, and Anjul Patney.
“FovVideoVDP : A Visible Difference Predictor for Wide Field-of-View Video.” ACM Transaction on Graphics 40, no. 4 (2021): 49. https://doi.org/10.1145/3450626.3459831.
and its supplementary materials, which can be found at:
https://www.cl.cam.ac.uk/research/rainbow/projects/fovvideovdp/
FovDots 是一项包含典型于视场聚焦渲染方法模拟瑕疵的视频质量数据集。该视频序列包含不同亮度级别的移动点（圆盘）。通过在大视场角处更稀疏地采样像素、使用修复绘画面法重构缺失像素以及应用滤波器以降低混叠瑕疵来模拟视场聚焦渲染。该数据集被用于校准和测试 FovVideoVDP：一种针对宽视场视频的可见差异预测器。数据集的详细信息可参考以下论文：Mantiuk, Rafał K.，Gyorgy Denes，Alexandre Chapiro，Anton Kaplanyan，Gizem Rufo，Romain Bachy，Trisha Lian，以及 Anjul Patney. “FovVideoVDP：一种针对宽视场视频的可见差异预测器。” ACM Transaction on Graphics 40, no. 4 (2021): 49. https://doi.org/10.1145/3450626.3459831。以及其补充材料，可从以下链接获取：https://www.cl.cam.ac.uk/research/rainbow/projects/fovvideovdp/。
提供机构：
Apollo
