Jon Barron
@jon_barron
AI researcher at Google DeepMind. Synthesized views are my own.
Here's my 3DV talk, in chapters: 1) Intro / NeRF boilerplate. 2) Recent reconstruction work. 3) Recent generative work. 4) Radiance fields as a field. 5) Why generative video has bitter-lessoned 3D. 6) Why generative video hasn't bitter-lessoned 3D. 5 & 6 are my favorites.
🚀 Just published in Nature Photonics: synthetic aperture waveguide holography—a new path toward ultra-thin, high-quality 3D mixed reality displays. 📄 nature.com/articles/s4156… #Photonics #Holography #MR 1/5
Want to be part of a team redefining SOTA for generative video models? Excited about building models that can reach billions of users? The Veo team is hiring! We are looking for amazing researchers and engineers, in North America and Europe. Details below:
People have asked me how to cite this talk, so here's a bibtex: @misc{Barron20253DV, author = {Jonathan T. Barron}, title = {Radiance Fields and the Future of Generative Media}, howpublished = {\url{youtube.com/watch?v=hFlF33…}}, year = {2025}, note = {Presented at 3DV} }
Here's my 3DV talk, in chapters: 1) Intro / NeRF boilerplate. 2) Recent reconstruction work. 3) Recent generative work. 4) Radiance fields as a field. 5) Why generative video has bitter-lessoned 3D. 6) Why generative video hasn't bitter-lessoned 3D. 5 & 6 are my favorites.
Veo 3 is out! Audio is the big new thing, but don't sleep on the image->video model. Here is `Documentary footage of a man as his ears grow and unfold and morph into gigantic elephant-sized ears. He is unconcerned, as he tells the viewer the benefits of having gigantic ears.`