We propose a real-world dataset of stereoscopic videos for color-mismatch correction. It includes real-world distortions achieved using a beam splitter. Our dataset is larger than any other for this task. We compared eight color-mismatch-correction methods on artificial and real-world datasets and showed that local methods are best suited to artificial distortions and that global methods are best suited to real-world distortions. Our efforts improved on the latest local neural-network method for color-mismatch correction in stereoscopic images, making it work faster and better on both artificial and real-world distortions.