HEADSET: Human Emotion Awareness under Partial Occlusions Multimodal DataSET

The volumetric representation of human interactions is one of the fundamental domains in the development of immersivemedia productions and telecommunication applications. Particularly in the context of the rapid advancement of Extended Reality(XR) applications, this volumetric data has proven to be an essential technology for future XR elaboration. In this work, we present anew multimodal database to help advance the development of immersive technologies. Our proposed database provides ethicallycompliant and diverse volumetric data, in particular 27 participants displaying posed facial expressions and subtle body movementswhile speaking, plus 11 participants wearing head-mounted displays (HMDs). The recording system consists of a volumetric capture(VoCap) studio, including 31 synchronized modules with 62 RGB cameras and 31 depth cameras. In addition to textured meshes, pointclouds, and multi-view RGB-D data, we use one Lytro Illum camera for providing light field (LF) data simultaneously. Finally, we alsoprovide an evaluation of our dataset employment with regard to the tasks of facial expression classification, HMDs removal, and pointcloud reconstruction. The dataset can be helpful in the evaluation and performance testing of various XR algorithms, including but notlimited to facial expression recognition and reconstruction, facial reenactment, and volumetric video. HEADSET and its all associatedraw data and license agreement will be publicly available for research purposes.