Computational Imaging for Stop-Motion Animated Video Productions

Creating movies using stop-motion technology remains a fascinating approach for storytelling even in the era of digital cinema. A huge number of professional and semiprofessional clips that were produced as fan art can be watched on Internet video platforms and serve as testimonial for the unbroken interest in unleashing creative potential using this technology. However, producing content using stop motion remains a cumbersome task that raises production costs, especially for full-length movies. Consequently, a trend can be observed even for successful television series that were originally produced using stop motion in which the production scheme was changed to computer animation. Against this background, we propose a production scheme for stop-motion-animated movies that has the potential to lower the production costs while increasing the quality of the resulting content. By using a static multicamera array and algorithms from the field of computational imaging, our technology allows artistic effects to be created in the post-production that are difficult to realize using conventional stop-motion production methods. Our approach allows changing the depth of field, smoothly moving the camera along virtual camera paths, and upsampling the frame rate of the stop-motion video in high quality. All effects are computed and applied in post-production, while all intrinsic and extrinsic parameters of the cameras remain static during the whole production. To demonstrate the practicability, results are shown from a stop-motion video that has been produced using the proposed approach.