DiVa-360: The Dynamic Visual Dataset for Immersive Neural Fields
DiVa-360: The Dynamic Visual Dataset for Immersive Neural Fields
复制标题
DOI：
--
复制
发表时间：
2023-07
期刊：
影响因子：
--
通讯作者：
Chengkun Lu;Peisen Zhou;Angela Xing;Chandradeep Pokhariya;Arnab Dey;Ishaan Shah;Rugved Mavidipalli;Dylan Hu;Andrew I. Comport;Kefan Chen;Srinath Sridhar
中科院分区：
文献类型：
--
作者：
Chengkun Lu;Peisen Zhou;Angela Xing;Chandradeep Pokhariya;Arnab Dey;Ishaan Shah;Rugved Mavidipalli;Dylan Hu;Andrew I. Comport;Kefan Chen;Srinath Sridhar
神经领域的进步使得能够高保真地捕捉动态3D场景的形状和外观。然而，由于算法挑战和缺乏大规模多视图真实世界数据集，它们的功能落后于传统表示（如2D视频）。我们解决数据集的限制与DiVa-360，一个真实世界的360动态视觉数据集，包含同步的高分辨率和长时间的多视图视频序列的表规模的场景捕获使用定制的低成本系统与53个摄像头。它包含21个对象为中心的序列分类不同的运动类型，25个复杂的手对象交互序列，和8个长时间序列，共17.4 M图像帧。此外，我们还提供前景-背景分割掩码、同步音频和文本描述。我们在DiVa-360上对最先进的动态神经场方法进行了基准测试，并提供了有关长期神经场捕获的现有方法和未来挑战的见解。
Advances in neural fields are enabling high-fidelity capture of the shape and appearance of dynamic 3D scenes. However, their capabilities lag behind those offered by conventional representations such as 2D videos because of algorithmic challenges and the lack of large-scale multi-view real-world datasets. We address the dataset limitation with DiVa-360, a real-world 360 dynamic visual dataset that contains synchronized high-resolution and long-duration multi-view video sequences of table-scale scenes captured using a customized low-cost system with 53 cameras. It contains 21 object-centric sequences categorized by different motion types, 25 intricate hand-object interaction sequences, and 8 long-duration sequences for a total of 17.4 M image frames. In addition, we provide foreground-background segmentation masks, synchronized audio, and text descriptions. We benchmark the state-of-the-art dynamic neural field methods on DiVa-360 and provide insights about existing methods and future challenges on long-duration neural field capture.