Look Ma, no markers: holistic performance capture without the hassle

• Published in: ACM transactions on graphics 2024-12, Vol.43 (6), p.1-12, Article 235
• Main Authors: Hewitt, Charlie, Saleh, Fatemeh, Aliakbarian, Sadegh, Petikam, Lohit, Rezaeifar, Shideh, Florentin, Louis, Hosenie, Zafiirah, Cashman, Thomas J., Valentin, Julien, Cosker, Darren, Baltrusaitis, Tadas
• Format: Article
• Language: English
• Subjects: Animation; Artificial intelligence; Computer graphics; Computer vision; Computing methodologies; Motion capture; Rendering; Shape modeling
• ISSN: 0730-0301; 1557-7368
• DOI: 10.1145/3687772

We tackle the problem of highly-accurate, holistic performance capture for the face, body and hands simultaneously. Motion-capture technologies used in film and game production typically focus only on face, body or hand capture independently, involve complex and expensive hardware and a high degree of manual intervention from skilled operators. While machine-learning-based approaches exist to overcome these problems, they usually only support a single camera, often operate on a single part of the body, do not produce precise world-space results, and rarely generalize outside specific contexts. In this work, we introduce the first technique for markerfree, high-quality reconstruction of the complete human body, including eyes and tongue, without requiring any calibration, manual intervention or custom hardware. Our approach produces stable world-space results from arbitrary camera rigs as well as supporting varied capture environments and clothing. We achieve this through a hybrid approach that leverages machine learning models trained exclusively on synthetic data and powerful parametric models of human shape and motion. We evaluate our method on a number of body, face and hand reconstruction benchmarks and demonstrate state-of-the-art results that generalize on diverse datasets.