A Camera-Native Talking-Head Video Dataset for Various Computer Vision Tasks
Researchers have released a new dataset of talking-head videos captured natively by consumer webcams, aiming to improve computer vision research. The dataset includes 847 recordings, each 15 seconds long, from over 800 participants using various webcam devices in natural settings. These recordings are preserved with lossless compression and annotated with quality scores, offering a valuable resource for benchmarking video compression, super-resolution, and quality assessment models. AI
IMPACT Provides a large-scale, high-fidelity dataset to advance research in video compression, super-resolution, and quality assessment for real-time communication.