Michael Broxton

About me

I am a staff research scientist and leader of a research team in Project Starline at Google Labs. My expertise is in machine learning, optics, light field imaging, computer vision, remote sensing, and robotics. I've worked with a variety of imaging systems ranging from orbital camera platforms, light field microscopes, and light field camera arrays. I've also built many large-scale image processing systems that process terascale datasets for planetary remote sensing, calcium imaging in live animals, and light field video data for AR/VR applications. Back in the day I was part of a small team that brought Moon mode and Mars mode in Google Earth.

Prior to working at Google, I was a student in the Stanford Computer Graphics Laboratory where I completed my CS Ph.D. under Marc Levoy where I developed light field microscope imaging technology for neuroscience applications. I also briefly held a post-doctoral research position in Gordon Wetzstein's Computational Imaging Lab at Stanford. I received my M.Eng and undergraduate degree in 2005 at MIT in EECS, working at the MIT Media Lab with Joe Paradiso. I have also worked at NASA Ames Research Center in the Intelligest Robotics Group from 2005-2011 and at Los Alamos National Laboratory during early years of undergraduate study.

Selected Papers

	Quark: Real-time, High-resolution, and General Neural View Synthesis 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 SIGGRAPH Asia 2024 (Journal Paper). [Paper][Website]
	Inpaint3D: 3D Scene Content Generation using 2D Inpainting Diffusion Kira Prabhu, Jane Wu, Lynn Tsai, Peter Hedman, Dan B Goldman, Ben Poole, Michael Broxton ArXiv. [Paper][Website]
	Immersive Light Field Video with a Layered Mesh Representation Michael Broxton*, John Flynn*, Ryan Overbeck*, Daniel Erickson*, Peter Hedman, Matthew DuVall, Jason Dourgarian, Jay Busch, Matt Whalen, Paul Debevec SIGGRAPH 2020 (Conference Paper). [Paper][Website]
	DeepView: View Synthesis with Learned Gradient Descent John Flynn, Michael Broxton, Paul Debevec, Matthew DuVall, Graham Fyffe, Ryan Overbeck, Noah Snavely, Richard Tucker CVPR 2018 (Conference Paper). [Paper][Website]
	Wave optics theory and 3-D deconvolution for the light field microscope Michael Broxton, Logan Grosenick, Samuel Yang, Noy Cohen, Aaron Andalman, Karl Deisseroth, Marc Levoy Optics Express 2013 (Journal Paper). [Paper]
	Identification of cellular-activity dynamics across large tissue volumes in the mammalian brain Logan Grosenick*, Michael Broxton*, Christina K. Kim*, Conor Liston*, Ben Poole, Samuel Yang, Aaron Andalman, Edward Scharff, Noy Cohen, Ofer Yizhar, Charu Ramakrishnan, Surya Ganguli, Patrick Suppes, Marc Levoy, Karl Deisseroth bioRxiv, 2017 (Preprint). [Paper]
	3D Lunar Terrain Reconstruction from Apollo Images Michael J. Broxton, Ara V. Nefian, Zachary Moratto, Taemin Kim, Michael Lundy, and Aleksandr V. Segal ISVC 2009 (Conference paper). [Paper][Website][Code]
	The Ames Stereo Pipeline: Automated 3D Surface Reconstruction from Orbital Imagery Michael Broxton and Larry Edwards 39th Lunar and Planetary Science Conference, 2008 (abstract). [Paper][Website][Code]
	Localizing a sensor network via collaborative processing of global stimuli Michael Broxton, Josh Lifton, and Joseph Paradiso European Workshop on Wireless Sensor Networks, 2005 (Conference paper). [Paper][Website]

Presentations

	Volume Reconstruction and Resolution Limits for Three Dimensional Snapshot Microscopy PhD Defense Talk 2017. [Video]
	Large-Scale Functional Imaging with the Light Field Microscope CodeNeuro 2015. [Video]
	The NASA Vision Workbench: Reflections on Image Processing in C++ Matthew Hancher and Michael BroxtonWillow Garage, 2009 (invited talk). [Slides]