Neural light field 3D printing

• Published in: ACM transactions on graphics 2020-11, Vol.39 (6), p.1-12, Article 207
• Main Authors: Zheng, Quan, Babaei, Vahid, Wetzstein, Gordon, Seidel, Hans-Peter, Zwicker, Matthias, Singh, Gurprit
• Format: Article
• Language: English
• Subjects: Applied computing; Computer graphics; Computer-aided manufacturing; Computing methodologies; Machine learning; Machine learning approaches; Neural networks; Operations research; Shape modeling; Volumetric models
• ISSN: 0730-0301; 1557-7368
• DOI: 10.1145/3414685.3417879

Modern 3D printers are capable of printing large-size light-field displays at high-resolutions. However, optimizing such displays in full 3D volume for a given light-field imagery is still a challenging task. Existing light field displays optimize over relatively small resolutions using a few co-planar layers in a 2.5D fashion to keep the problem tractable. In this paper, we propose a novel end-to-end optimization approach that encodes input light field imagery as a continuous-space implicit representation in a neural network. This allows fabricating high-resolution, attenuation-based volumetric displays that exhibit the target light fields. In addition, we incorporate the physical constraints of the material to the optimization such that the result can be printed in practice. Our simulation experiments demonstrate that our approach brings significant visual quality improvement compared to the multilayer and uniform grid-based approaches. We validate our simulations with fabricated prototypes and demonstrate that our pipeline is flexible enough to allow fabrications of both planar and non-planar displays.