Ignacio Rocco

Research Scientist

Google DeepMind



I am a research scientist at Google DeepMind working in problems related to computer vision.

Previously, I was a post-doctoral researcher at Facebook AI Research (FAIR), working with Natalia Neverova and Andrea Vedaldi. Before, I completed my PhD at the Willow team, INRIA/ENS, working under the supervision of Josef Sivic and Relja Arandjelović developing trainable methods for solving the image alignment problem in difficult cases presenting strong appearance variations (including category-level matching and variations in depiction style), or changes in the scene due to the passage of time. Earlier, I got a Master's degree in Mathematics/Vision/Machine Learning from ENS Paris-Saclay.

News

05/2023 - I started as a Research Scientist in Google DeepMind.
03/2023 - 2 accepted papers at CVPR 2023.
04/2022 - I was awarded the best PhD thesis prize by AFRIF.
03/2022 - 2 accepted papers at CVPR 2022.
04/2021 - I started a post-doc at FAIR.
10/2020 - I graduated from my PhD. You can find the manuscript here.
07/2019 - Relja Arandjelović gave an Invited Talk presenting my work at BMVA's Geometry and Deep Learning Meeting.
04/2019 - Talk at IMAGINE group at ENPC.
03/2019 - Talk at SMILE seminar at Télécom Paris.
12/2018 - Spotlight oral at NeurIPS'18.
08/2017 - Talk at the Workshop on visual localization and geometric matching at CIIRC, CTU, Prague.
07/2017 - Spotlight oral at CVPR'17.
06/2017 - Attended the Deep Learning and Reinforcement Learning Summer School at MILA, Montreal.
06/2017 - Attended the Machine Learning Student Summit at Google Zurich.

Publications

Roman Shapovalov*, Yanir Kleiman*, Ignacio Rocco*, David Novotny, Andrea Vedaldi, Changan Chen, Filippos Kokkinos, Ben Graham, Natalia Neverova (*: equal contribution)
Replay: Multi-modal Multi-view Acted Videos for Casual Holography
In Proceedings of the International Conference on Computer Vision (ICCV), 2023.
[Project page][Paper on arXiv]


Ignacio Rocco, Iurii Makarov, Filippos Kokkinos, David Novotny, Benjamin Graham, Natalia Neverova, Andrea Vedaldi
Real-time volumetric rendering of dynamic humans
arXiv, 2023.
[Project page][Paper on arXiv]


Nikita Karaev, Ignacio Rocco, Benjamin Graham, Natalia Neverova, Andrea Vedaldi, Christian Rupprecht
DynamicStereo: Consistent Dynamic Depth from Stereo Videos
In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2023.
[Project page][Paper on arXiv]


Samarth Sinha, Roman Shapovalov, Jeremy Reizenstein, Ignacio Rocco, Natalia Neverova, Andrea Vedaldi, David Novotny
Common pets in 3d: Dynamic new-view synthesis of real-life deformable categories
In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2023.


D. Novotny, I. Rocco, S. Sinha, A. Carlier, G. Kerchenbaum, R. Shapovalov, N. Smetanin, N. Neverova, B. Graham, A. Vedaldi
KeyTr: Keypoint Transporter for 3D Reconstruction of Deformable Objects in Videos
In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2022. (Oral)



A. Ianina, N. Sarafianos, Y. Xu, I. Rocco, T. Tung
BodyMap: Learning Full-Body Dense Correspondence Map
In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2022.
[Project page][Paper on arXiv]



D. Zhukov, I. Rocco, I. Laptev, J. Sivic, J.L. Schoenberger, B. Tekin, M. Pollefeys
Reconstructing and grounding narrated instructional videos in 3D
arXiv preprint arXiv:2109.04409, 2021.
[Paper on arXiv]



I. Rocco, R. Arandjelović and J. Sivic
Efficient Neighbourhood Consensus Networks via Submanifold Sparse Convolutions
In Proceedings of the European Conference on Computer Vision (ECCV), 2020.
[Project page][Paper on arXiv][PyTorch code]



H. Taira, I. Rocco, J. Sedlar, M. Okutomi, J. Sivic, T. Pajdla, T. Sattler, A. Torii
Is This The Right Place? Geometric-Semantic Pose Verification for Indoor Visual Localization
In Proceedings of the International Conference on Computer Vision (ICCV), 2019.
[Project page][Paper on arXiv]



M. Dusmanu, I. Rocco, T. Pajdla, M. Pollefeys, J. Sivic, A. Torii, T. Sattler
D2-Net: A Trainable CNN for Joint Detection and Description of Local Features
In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2019.
[Project page][Paper on arXiv][PyTorch code]



I. Rocco, M. Cimpoi, R. Arandjelović, A. Torii, T. Pajdla and J. Sivic
Neighbourhood Consensus Networks
In Proceedings of the 32nd Conference on Neural Information Processing Systems (NeurIPS), 2018. (Spotlight)
[Project page][Paper on arXiv][PyTorch code][Spotlight oral]



I. Rocco, R. Arandjelović and J. Sivic
End-to-end weakly-supervised semantic alignment
In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2018.
[Project page][Paper on arXiv][PyTorch code]



I. Rocco, R. Arandjelović and J. Sivic
Convolutional neural network architecture for geometric matching
In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2017. (Spotlight)
[Project page][Paper on arXiv][MatConvNet code][PyTorch code][Spotlight oral]



I. Rocco, M. Goncalves Almeida Antunes, D. Aouada and B. Ottersten
RGB-D and Thermal Sensor Fusion
In 11th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISAPP), 2016.
[Paper on Scitepress][PDF]

Teaching

Teaching assistant for the Object Recognition and Computer Vision course of ENS Paris Saclay's MVA M2 Master on the 2016, 2017 and 2018 editions.

Misc.

I have reviewed for CVPR, ECCV, BMVC, NeurIPS, T-PAMI, and other conferences and journals.