Ego-1K -- A Large-Scale Multiview Video Dataset for Egocentric Vision
This dataset addresses the need for benchmarking egocentric scene reconstruction methods, which is important as smart glasses with multiple cameras become more common, but it is incremental as it primarily provides new data rather than novel algorithms.
The authors introduced Ego-1K, a large-scale multiview video dataset with nearly 1,000 short egocentric videos captured using 12 synchronized cameras, focusing on hand motions and interactions to advance neural 3D video synthesis and dynamic scene understanding, and they found it presents unique challenges for existing methods due to large disparities and motion.
We present Ego-1K, a large-scale collection of time-synchronized egocentric multiview videos designed to advance neural 3D video synthesis and dynamic scene understanding. The dataset contains nearly 1,000 short egocentric videos captured with a custom rig with 12 synchronized cameras surrounding a 4-camera VR headset worn by the user. Scene content focuses on hand motions and hand-object interactions in different settings. We describe rig design, data processing, and calibration. Our dataset enables new ways to benchmark egocentric scene reconstruction methods, an important research area as smart glasses with multiple cameras become omnipresent. Our experiments demonstrate that our dataset presents unique challenges for existing 3D and 4D novel view synthesis methods due to large disparities and image motion caused by close dynamic objects and rig egomotion. Our dataset supports future research in this challenging domain. It is available at https://huggingface.co/datasets/facebook/ego-1k.