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

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.

1. Introduction

Neural fields [69], or neural implicit representations, have recently emerged as useful representations in computer vision, graphics, and robotics [60], [69] for capturing properties such as radiance [4], [5], [27], [43],[4] [4], shape [32], [41], [45], [46], [64], [74], and dynamic motion [9], [17], [31], [36], [38], [48], [63], [65], [67]. Their high fidelity, continuous representation, and implicit compression [15] properties make them attractive as immersive digital representations of our dynamic world.