Jun Saito

Senior Research Engineer

Seattle

Jun was born and raised in Tokyo, Japan. After receiving his BS degree from the University of Tokyo, he spent three years living in Hawaii while working on a massively parallel global illumination renderer at Square USA. After Square shut down the office in paradise, Jun worked on facial animation research at Marza, the animation division of Sega. At the same time, he kicked off a collaborative research project with the University of Edinburgh, working on the problem of production-quality locomotion synthesis and resulting in the SIGGRAPH 2017 paper “Phase-Functioned Neural Networks for Character Control.” At Method Studios, Jun was responsible for research and development of high-fidelity digital characters for visual effects in many Marvel films such as “Doctor Strange,” “Guardians of the Galaxy 2,” “Thor: Ragnarok,” and more. His recent research has been in character animation, physically-based animation, geometry processing, and machine/deep learning, though he is passionate to work on anything related to helping artists.

Publications

Neural Jacobian Fields: Learning Intrinsic Mappings of Arbitrary Meshes

Aigerman, N., Gupta, K., Kim, V., Chaudhuri, S., Saito, J., Groueix, T. (Aug. 8, 2022)

SIGGRAPH

Skeleton-free Pose Transfer for Stylized 3D Characters

Liao, Z., Yang, J., Saito, J., Pons-Moll, G., Zhou, Y. (Jul. 28, 2022)

ECCV 2022

Audio-Driven Neural Gesture Reenactment With Video Motion Graphs

Zhou, Y., Yang, J., Li, D., Saito, J., Aneja, D., Kalogerakis, E. (Jun. 24, 2022)

IEEE / CVF Computer Vision and Pattern Recognition Conference (CVPR)

Neural Puppet: Generative Layered Cartoon Characters

Poursaeed, O., Kim, V., Shechtman, E., Saito, J., Belongie, S., Shechtman, E. (Mar. 1, 2020)

Winter Conference on Applications of Computer Vision (WACV'20)

News