Ignacio Rocco

39 papers A* 12A 1Journal 22Unranked 3
YearRankTypeTitle / Venue / Authors
2025 A* conf
Direct Motion Models for Assessing Generated Videos.
ICML
Kelsey R. Allen, Carl Doersch, Guangyao Zhou, Mohammed Suhail, Danny Driess, Ignacio Rocco, Yulia Rubanova, Thomas Kipf, Mehdi S. M. Sajjadi, Kevin Patrick Murphy, João Carreira, Sjoerd van Steenkiste
2025 J jnl
Direct Motion Models for Assessing Generated Videos.
CoRR
Kelsey R. Allen, Carl Doersch, Guangyao Zhou, Mohammed Suhail, Danny Driess, Ignacio Rocco, Yulia Rubanova, Thomas Kipf, Mehdi S. M. Sajjadi, Kevin Murphy, João Carreira, Sjoerd van Steenkiste
2025 J jnl
Efficiently Reconstructing Dynamic Scenes One D4RT at a Time.
CoRR
Chuhan Zhang, Guillaume Le Moing, Skanda Koppula, Ignacio Rocco, Liliane Momeni, Junyu Xie, Shuyang Sun, Rahul Sukthankar, Joëlle K. Barral, Raia Hadsell, Zoubin Ghahramani, Andrew Zisserman, Junlin Zhang, Mehdi S. M. Sajjadi
2025 J jnl
TAPNext: Tracking Any Point (TAP) as Next Token Prediction.
CoRR
Artem Zholus, Carl Doersch, Yi Yang, Skanda Koppula, Viorica Patraucean, Xu Owen He, Ignacio Rocco, Mehdi S. M. Sajjadi, Sarath Chandar, Ross Goroshin
2024 — conf
BootsTAP: Bootstrapped Training for Tracking-Any-Point.
ACCV (2)
Carl Doersch, Pauline Luc, Yi Yang, Dilara Gokay, Skanda Koppula, Ankush Gupta, Joseph Heyward, Ignacio Rocco, Ross Goroshin, João Carreira, Andrew Zisserman
2024 J jnl
BootsTAP: Bootstrapped Training for Tracking-Any-Point.
CoRR
Carl Doersch, Yi Yang, Dilara Gokay, Pauline Luc, Skanda Koppula, Ankush Gupta, Joseph Heyward, Ignacio Rocco, Ross Goroshin, João Carreira, Andrew Zisserman
2024 — conf
CoTracker: It Is Better to Track Together.
ECCV (62)
Nikita Karaev, Ignacio Rocco, Benjamin Graham, Natalia Neverova, Andrea Vedaldi, Christian Rupprecht
2024 J jnl
Scaling 4D Representations.
CoRR
João Carreira, Dilara Gokay, Michael King, Chuhan Zhang, Ignacio Rocco, Aravindh Mahendran, Thomas Keck, Joseph Heyward, Skanda Koppula, Etienne Pot, Goker Erdogan, Yana Hasson, Yi Yang, Klaus Greff, Guillaume Le Moing, Sjoerd van Steenkiste, Daniel Zoran, Drew A. Hudson, Pedro Vélez, Luisa F. Polanía, Luke Friedman, Chris Duvarney, Ross Goroshin, Kelsey R. Allen, Jacob C. Walker, Rishabh Kabra, Eric Aboussouan, Jennifer J. Sun, Thomas Kipf, Carl Doersch, Viorica Patraucean, Dima Damen, Pauline Luc, Mehdi S. M. Sajjadi, Andrew Zisserman
2024 A* conf
TAPVid-3D: A Benchmark for Tracking Any Point in 3D.
NeurIPS
Skanda Koppula, Ignacio Rocco, Yi Yang, Joseph Heyward, João Carreira, Andrew Zisserman, Gabriel Brostow, Carl Doersch
2024 J jnl
TAPVid-3D: A Benchmark for Tracking Any Point in 3D.
CoRR
Skanda Koppula, Ignacio Rocco, Yi Yang, Joseph Heyward, João Carreira, Andrew Zisserman, Gabriel Brostow, Carl Doersch
2023 J jnl
CoTracker: It is Better to Track Together.
CoRR
Nikita Karaev, Ignacio Rocco, Benjamin Graham, Natalia Neverova, Andrea Vedaldi, Christian Rupprecht
2023 A* conf
Common Pets in 3D: Dynamic New-View Synthesis of Real-Life Deformable Categories.
CVPR
Samarth Sinha, Roman Shapovalov, Jeremy Reizenstein, Ignacio Rocco, Natalia Neverova, Andrea Vedaldi, David Novotný
2023 A* conf
DynamicStereo: Consistent Dynamic Depth from Stereo Videos.
CVPR
Nikita Karaev, Ignacio Rocco, Benjamin Graham, Natalia Neverova, Andrea Vedaldi, Christian Rupprecht
2023 J jnl
DynamicStereo: Consistent Dynamic Depth from Stereo Videos.
CoRR
Nikita Karaev, Ignacio Rocco, Benjamin Graham, Natalia Neverova, Andrea Vedaldi, Christian Rupprecht
2023 J jnl
Real-time volumetric rendering of dynamic humans.
CoRR
Ignacio Rocco, Iurii Makarov, Filippos Kokkinos, David Novotný, Benjamin Graham, Natalia Neverova, Andrea Vedaldi
2023 A* conf
Replay: Multi-modal Multi-view Acted Videos for Casual Holography.
ICCV
Roman Shapovalov, Yanir Kleiman, Ignacio Rocco, David Novotný, Andrea Vedaldi, Changan Chen, Filippos Kokkinos, Benjamin Graham, Natalia Neverova
2023 J jnl
Replay: Multi-modal Multi-view Acted Videos for Casual Holography.
CoRR
Roman Shapovalov, Yanir Kleiman, Ignacio Rocco, David Novotný, Andrea Vedaldi, Changan Chen, Filippos Kokkinos, Benjamin Graham, Natalia Neverova
2023 A conf
Self-supervised Correspondence Estimation via Multiview Registration.
WACV
Mohamed El Banani, Ignacio Rocco, David Novotný, Andrea Vedaldi, Natalia Neverova, Justin Johnson, Benjamin Graham
2022 A* conf
BodyMap: Learning Full-Body Dense Correspondence Map.
CVPR
Anastasia Ianina, Nikolaos Sarafianos, Yuanlu Xu, Ignacio Rocco, Tony Tung
2022 J jnl
BodyMap: Learning Full-Body Dense Correspondence Map.
CoRR
Anastasia Ianina, Nikolaos Sarafianos, Yuanlu Xu, Ignacio Rocco, Tony Tung
2022 J jnl
Common Pets in 3D: Dynamic New-View Synthesis of Real-Life Deformable Categories.
CoRR
Samarth Sinha, Roman Shapovalov, Jeremy Reizenstein, Ignacio Rocco, Natalia Neverova, Andrea Vedaldi, David Novotný
2022 A* conf
KeyTr: Keypoint Transporter for 3D Reconstruction of Deformable Objects in Videos.
CVPR
David Novotný, Ignacio Rocco, Samarth Sinha, Alexandre Carlier, Gael Kerchenbaum, Roman Shapovalov, Nikita Smetanin, Natalia Neverova, Benjamin Graham, Andrea Vedaldi
2022 J jnl
NCNet: Neighbourhood Consensus Networks for Estimating Image Correspondences.
IEEE Trans. Pattern Anal. Mach. Intell.
Ignacio Rocco, Mircea Cimpoi, Relja Arandjelovic, Akihiko Torii, Tomás Pajdla, Josef Sivic
2022 J jnl
Self-Supervised Correspondence Estimation via Multiview Registration.
CoRR
Mohamed El Banani, Ignacio Rocco, David Novotný, Andrea Vedaldi, Natalia Neverova, Justin Johnson, Benjamin Graham
2021 J jnl
Reconstructing and grounding narrated instructional videos in 3D.
CoRR
Dimitri Zhukov, Ignacio Rocco, Ivan Laptev, Josef Sivic, Johannes L. Schönberger, Bugra Tekin, Marc Pollefeys
2020 — conf
Efficient Neighbourhood Consensus Networks via Submanifold Sparse Convolutions.
ECCV (9)
Ignacio Rocco, Relja Arandjelovic, Josef Sivic
2020 J jnl
Efficient Neighbourhood Consensus Networks via Submanifold Sparse Convolutions.
CoRR
Ignacio Rocco, Relja Arandjelovic, Josef Sivic
2020 — —
Neural architectures for estimating correspondences between images. (Estimation des correspondances entre images par réseaux de neurones convolutifs).
Ignacio Rocco
2019 J jnl
Convolutional Neural Network Architecture for Geometric Matching.
IEEE Trans. Pattern Anal. Mach. Intell.
Ignacio Rocco, Relja Arandjelovic, Josef Sivic
2019 A* conf
D2-Net: A Trainable CNN for Joint Description and Detection of Local Features.
CVPR
Mihai Dusmanu, Ignacio Rocco, Tomás Pajdla, Marc Pollefeys, Josef Sivic, Akihiko Torii, Torsten Sattler
2019 J jnl
D2-Net: A Trainable CNN for Joint Detection and Description of Local Features.
CoRR
Mihai Dusmanu, Ignacio Rocco, Tomás Pajdla, Marc Pollefeys, Josef Sivic, Akihiko Torii, Torsten Sattler
2019 J jnl
Is This The Right Place? Geometric-Semantic Pose Verification for Indoor Visual Localization.
CoRR
Hajime Taira, Ignacio Rocco, Jirí Sedlár, Masatoshi Okutomi, Josef Sivic, Tomás Pajdla, Torsten Sattler, Akihiko Torii
2019 A* conf
Is This the Right Place? Geometric-Semantic Pose Verification for Indoor Visual Localization.
ICCV
Hajime Taira, Ignacio Rocco, Jirí Sedlár, Masatoshi Okutomi, Josef Sivic, Tomás Pajdla, Torsten Sattler, Akihiko Torii
2018 A* conf
End-to-End Weakly-Supervised Semantic Alignment.
CVPR
Ignacio Rocco, Relja Arandjelovic, Josef Sivic
2018 A* conf
Neighbourhood Consensus Networks.
NeurIPS
Ignacio Rocco, Mircea Cimpoi, Relja Arandjelovic, Akihiko Torii, Tomás Pajdla, Josef Sivic
2018 J jnl
Neighbourhood Consensus Networks.
CoRR
Ignacio Rocco, Mircea Cimpoi, Relja Arandjelovic, Akihiko Torii, Tomás Pajdla, Josef Sivic
2017 A* conf
Convolutional Neural Network Architecture for Geometric Matching.
CVPR
Ignacio Rocco, Relja Arandjelovic, Josef Sivic
2017 J jnl
Convolutional neural network architecture for geometric matching.
CoRR
Ignacio Rocco, Relja Arandjelovic, Josef Sivic
2017 J jnl
End-to-end weakly-supervised semantic alignment.
CoRR
Ignacio Rocco, Relja Arandjelovic, Josef Sivic