DiVa-360: The Dynamic Visual Dataset for Immersive Neural Fields

arXiv:2307.16897v2 Announce Type: replace
Abstract: 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 …

3d scenes abstract advances arxiv capabilities challenges cs.ai cs.cv dataset datasets dynamic enabling fidelity fields however immersive scale type videos view visual world