360°全景视频 数据集Dataset
Kaggle: Your Machine Learning and Data Science Community
这个平台提供了很多数据集和ML模型
加入超过2600万机器学习者，分享，压力测试，并保持最新的ML技术和技术。为您的下一个项目发现社区发布的模型，数据和代码的巨大存储库。
| 数据集 | 参考文献 | 下载地址 | |
|---|---|---|---|
| 360UHD | 超分辨率任务 | A. Agrahari Baniya, T. -K. Lee, P. W. Eklund and S. Aryal, “Omnidirectional Video Super-Resolution Using Deep Learning,” in IEEE Transactions on Multimedia, vol. 26, pp. 540-554, 2024, doi: 10.1109/TMM.2023.3267294 | 360 Ultra HD (360UHD) |
| 360VDS | 大规模、低分辨率 该数据集包含590个ERP全景视频。全景帧被调整为256 × 512，并在训练过程中随机翻转。 | A. A. Baniya, T.-K. Lee, P. W. Eklund, and S. Aryal, “Omnidirectional video super-resolution using deep learning,” IEEE Trans. Multimedia, vol. 26, pp. 540–554, 2023 | https://drive.google.com/drive/folders/1tYiyoPmCkPPrJ1l3dnBvZTqVMH4WMvbx?usp=sharing |
| Eye Tracking | 208个全景视频，分辨率为960×1920。 | Y. Xu et al., “Gaze Prediction in Dynamic 360° Immersive Videos,” 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, Salt Lake City, UT, USA, 2018, pp. 5333-5342, doi: 10.1109/CVPR.2018.00559. keywords: {Videos;Gaze tracking;Resists;Task analysis;Saliency detection;Games;Cameras}, | Eye Tracking dataset [Baidu Pan] code: kdcj |
| VR-HM48 | 40个受试者在观看全景视频时的观看方向数据。在我们的数据库中总共有48个全景视频序列。 | M. Xu, C. Li, Y. Liu, X. Deng, and J. Lu, “A subjective visual quality assessment method of panoramic videos,” in 2017 IEEE International Conference on Multimedia and Expo (ICME), 2017, pp. 517–522. | https://github.com/Archer-Tatsu/head-tracking?tab=readme-ov-file |
| AVTrack360 | 用HDM观看xyz三个轴的旋转角度。注视跟踪数据集，48人（25女\23男）观看20个长30s的不同全方位视频。 | S. Fremerey, A. Singla, K. Meseberg, and A. Raake, “AVtrack360: an open dataset and software recording people’s head rotations watching 360 videos on an HMD,” in Proceedings of the 9th ACM multimedia systems conference, 2018, pp. 403–408. | GitHub - acmmmsys/2018-AVTrack360: A repository containing the source code for the paper “AVTrack360: An Open Dataset and Software Recording People’s Head Rotations Watching 360° Videos on an HMD” |
另外几个用于测试的图像集
| 数据集 | 特点 | 参考文献 |
|---|---|---|
| CIFAR10 | 常用的手写图像数据库 | A. Krizhevsky, “Learning multiple layers of features from tiny images,” M.S. thesis, Dept. Eng., Univ. Tront, Toronto, ON, Canada, 2009. |
| CLIC2021 | 60 images, up to 2048 × 1890 pixels | (2021). CLIC 2021: Challenge on Learned Image Compression. [Online]. Available: http://compression.cc |
| Open Images Dataset | A. Kuznetsova et al, “The open images dataset v4,” Int. J. Comput. Vis., vol. 128, no. 7, pp. 1–26, 2020. |