Ricardo Martin-Brualla

Contact: rmbrualla@gmail.com

Hi! I am Ricardo Martin-Brualla, and I do research at the intersection of Computer Vision, Computer Graphics and Machine Learning. I am interested in learning-based techniques that supplement existing 3D reconstruction pipelines to generate beautiful visuals.

I work at Google in Seattle on the future of communication. In the fall of 2018, I taught Computer Vision at University of Washington. Previously, I obtained my PhD at Computer Science and Engineering at the University of Washington under the supervision of Steve Seitz and finished in June 2016. Before, I obtained undergraduate degrees in Math and Computer Science at Barcelona Tech / UPC, as part of the interdisciplinary center CFIS. I grew up in Madrid, although I was schooled in the German high school system.

I love traveling and seeing other parts of the world. After my undergraduate studies, I traveled by bicycle around New Zealand, visiting the antipodes of my house in Madrid. I also visited Vanuatu and climbed a volcano to see lava bubbling. After my PhD, I backpacked across Iceland, and explored Madagascar and Central Asia. I enjoy backcountry skiing and my latest challenge has been sea kayaking!

In Spring and Summer 2021, I will be crossing Alaska on foot, paddling and biking, from Ketchikan to Kotzebue. We will be writing a blog on north2arctic.com.

Publications (Google scholar)

Deformable Neural Radiance Fields
Keunhong Park, Utkarsh Sinha, Jonathan T. Barron, Sofien Bouaziz, Dan B Goldman, Steven M. Seitz, Ricardo Martin-Brualla
Arxiv preprint.
[paper, video, website]
NeRF in the Wild: Neural Radiance Fields for Unconstrained Photo Collections
Ricardo Martin-Brualla*, Noha Radwan*, Mehdi S. M. Sajjadi*, Jonathan T. Barron, Alexey Dosovitskiy, Daniel Duckworth
Arxiv preprint.
[paper, video, website]
KeystoneDepth: Visualizing History in 3D
Xuan Luo, Yanmeng Kong, Jason Lawrence, Ricardo Martin-Brualla, Steve Seitz
3DV 2020.
[paper, video, website]
GeLaTO: Generative Latent Textured Objects
Ricardo Martin-Brualla, Rohit Pandey, Sofien Bouaziz, Matthew Brown, Dan B Goldman
ECCV 2020 (spotlight).
[paper, video, website]
State of the Art on Neural Rendering
Ayush Tewari, Ohad Fried, Justus Thies, Vincent Sitzmann, Stephen Lombardi, Kalyan Sunkavalli, Ricardo Martin-Brualla, Tomas Simon, Jason Saragih, Matthias Nießner, Rohit Pandey, Sean Fanello, Gordon Wetzstein, Jun-Yan Zhu, Christian Theobalt, Maneesh Agrawala, Eli Shechtman, Dan B Goldman, Michael Zollhöfer
EUROGRAPHICS 2020 (State of the Art Report).
Multi-View Image Fusion
Marc Comino Trinidad, Ricardo Martin-Brualla, Florian Kainz, Janne Kontkanen
ICCV 2019 (poster).
Neural Rerendering in the Wild
Moustafa Meshry, Dan B Goldman, Sameh Khamis, Hugues Hoppe, Rohit Pandey, Noah Snavely, Ricardo Martin-Brualla
CVPR 2019 (oral). Best Paper Award Finalist (top 1% of submissions)
[paper, video, code]
Volumetric Capture of Humans with a Single RGBD Camera via Semi-Parametric Learning
Rohit Pandey, Anastasia Tkach, Shuoran Yang, Pavel Pidlypenskyi, Jonathan Taylor, Ricardo Martin-Brualla, Andrea Tagliasacchi, George Papandreou, Philip Davidson, Cem Keskin, Shahram Izadi, Sean Fanello
CVPR 2019 (poster).
[paper, video]
LookinGood: Enhancing Performance Capture with Real-time Neural Re-Rendering
Ricardo Martin-Brualla*, Rohit Pandey*, Shuoran Yang, Pavel Pidlypenskyi, Jonathan Taylor, Julien Valentin, Sameh Khamis, Philip Davidson, Anastasia Tkach, Peter Lincoln, Adarsh Kowdle, Christoph Rhemann, Dan B Goldman, Cem Keskin, Steve Seitz, Shahram Izadi, Sean Fanello
Siggraph Asia 2018.
[paper, video]
Seattle 3 Year Time-lapse Video from the Space Needle
Ricardo Martin-Brualla
Hackernoon, 2018.
[blog, video, make-of]
Press: Seattle Times, PetaPixel, GeekWire
More than 500k views on Youtube!
3D Time-lapse Reconstruction from Internet Photos
Ricardo Martin-Brualla, David Gallup, Steven M. Seitz
International Journal on Computer Vision (IJCV) 2017.
3D Time-lapse Reconstruction from Internet Photos
Ricardo Martin-Brualla, David Gallup, Steven M. Seitz
International Conference on Computer Vision (ICCV 2015) (oral presentation).
[paper, project page, video]
Press: PetaPixel
Time-lapse Mining from Internet Photos
Ricardo Martin-Brualla, David Gallup, Steven M. Seitz
Proceedings of ACM SIGGRAPH 2015.
[paper, project page, video]
Press: interviews at WIRED, BBC, Seattle Times and featured in Washington Post, Gizmodo, CNET, etc.
More than 1.5 million Youtube views!
The 3D jigsaw puzzle: mapping large indoor spaces
Ricardo Martin-Brualla, Yanling He, Bryan C. Russell, Steven M. Seitz.
Proceedings of the 13th European Conference on Computer Vision, (ECCV 2014).
[paper, project page, video]
3D Wikipedia: Using Online Text to Automatically Label and Navigate Reconstructed Geometry
Bryan C. Russell, Ricardo Martin-Brualla, Daniel J. Butler, Steven M. Seitz, and Luke Zettlemoyer.
ACM Transactions on Graphics (SIGGRAPH Asia 2013), Vol. 32, No. 6.
[paper, project page, video]
Press: New Scientist, Gizmodo

Viewport: A Fully Distributed Immersive Teleconferencing System with Infrared Dot Pattern
Cha Zhang, Qin Cai, Phillip Chou, Zhengyou Zhang, Ricardo Martin-Brualla
IEEE Multimedia Magazine, pp. 17-27, Vol. 20, No. 1, Jan.-Mar. 2013.
Instance Sense Induction from Attribute Sets
Ricardo Martin-Brualla, Enrique Alfonseca, Marius Pasca, Keith Hall, Enrique Robledo-Arnuncio, Massimiliano Ciaramita
Proceedings of the 23rd International Conference on Computational Linguistics: Posters (COLING-2010), pp. 819-827
The Role of Query Sessions in Extracting Instance Attributes from Web Search Queries
Marius Pasca, Enrique Alfonseca, Enrique Robledo-Arnuncio, Ricardo Martin-Brualla, Keith Hall.
Proceedings of the 32nd European Conference on Information Retrieval (ECIR-2010), pp. 62-74.