Hi! I’m Kathryn.
Senior Research Scientist at Google Beam. Previously an AI Resident at Google [X] and a Ph.D. student at Harvard SEAS. My research focuses on high-fidelity real-time novel view synthesis. My dissertation was on algebraic geometry for computer vision.
Recent publications:
Youming Deng, Songyou Peng, Junyi Zhang, Kathryn Heal, Tiancheng Sun, John Flynn, Steve Marschner, and Lucy Chai. 2026. Selfi: Self Improving Reconstruction Engine via 3D Geometric Feature Alignment. arXiv preprint arXiv:2512.08930. Accepted to CVPR 2026.
Tooba Imtiaz, Lucy Chai, Kathryn Heal, Xuan Luo, Jungyeon Park, Jennifer Dy, and John Flynn. 2025. LVT: Large-Scale Scene Reconstruction via Local View Transformers. In Proceedings of the SIGGRAPH Asia 2025 Conference Papers (SA Conference Papers ’25). Association for Computing Machinery, New York, NY, USA, Article 196, 1–12. https://doi.org/10.1145/3757377.3763838
John Flynn, Michael Broxton, Lukas Murmann, Lucy Chai, Matthew DuVall, Clément Godard, Kathryn Heal, Srinivas Kaza, Stephen Lombardi, Xuan Luo, Supreeth Achar, Kira Prabhu, Tiancheng Sun, Lynn Tsai, and Ryan Overbeck. 2024. Quark: Real-time, High-resolution, and General Neural View Synthesis. ACM Trans. Graph. 43, 6, Article 194 (December 2024), 20 pages. https://doi.org/10.1145/3687953
Research
Developing fast, generalizable novel view synthesis for high-fidelity 3D communication.
Applying algebraic geometry to solve classical problems in shape-from-shading and lighting invariance.
Education
Ph.D. Applied Math, Harvard University.
B.S.
Applied Math, University of California Los Angeles.
kathryn heal, ph.d. 