Publications
2024
Walid Bousselham, Felix Petersen, Vittorio Ferrari, Hilde Kuehne
Grounding Everything: Emerging Localization Properties in Vision-Language Transformers
IEEE Computer Vision and Pattern Recognition (CVPR), 2024.
2023
Denys Rozumnyi, Stefan Popov, Kevis-Kokitsi Maninis, Matthias Nießner, Vittorio Ferrari
Estimating Generic 3D Room Structures from 2D Annotations
NeurIPS Dataset and Benchmarks track (NeuIPS), 2023
Varun Jampani, Kevis-Kokitsi Maninis, Andreas Engelhardt, Arjun Karpur, Karen Truong, Kyle Sargent, Stefan Popov, André Araujo, Ricardo Martin-Brualla, Kaushal Patel, Daniel Vlasic, Vittorio Ferrari, Ameesh Makadia, Ce Liu, Yuanzhen Li, Howard Zhou
NeurIPS Dataset and Benchmarks track (NeuIPS), 2023
Emanuele Bugliarello, Hernan Moraldo, Ruben Villegas, Mohammad Babaeizadeh, Mohammad Taghi Saffar, Han Zhang, Dumitru Erhan, Vittorio Ferrari, Pieter-Jan Kindermans, Paul Voigtlaender
NeurIPS Dataset and Benchmarks track (NeuIPS), 2023
Kevis-Kokitsi Maninis, Stefan Popov, Matthias Nießner, Vittorio Ferrari
CAD-Estate: Large-scale CAD Model Annotation in RGB Videos
International Conference on Computer Vision (ICCV), 2023
Thomas Mensink, Jasper Uijlings, Lluis Castrejon, Arushi Goel, Felipe Cadar, Howard Zhou, Fei Sha, André Araujo, Vittorio Ferrari
Encyclopedic VQA: Visual questions about detailed properties of fine-grained categories
International Conference on Computer Vision (ICCV), 2023
Denys Rozumnyi, Jiri Matas, Marc Pollefeys, Vittorio Ferrari, Martin R. Oswald
International Conference on Computer Vision (ICCV), 2023
Otilia Stretcu, Edward Vendrow, Kenji Hata, Krishnamurthy Viswanathan, Vittorio Ferrari, Sasan Tavakkol, Wenlei Zhou, Aditya Avinash, Enming Luo, Neil Gordon Alldrin, Mohammad Bateni, Gabriel Berger, Andrew Bunner, Chun-Ta Lu, Javier Rey, Giulia DeSalvo, Ranjay Krishna, Ariel Fuxman
Agile Modeling: From Concept to Classifier in Minutes
International Conference on Computer Vision (ICCV), 2023
Paul Voigtlaender, Soravit Changpinyo, Jordi Pont-Tuset, Radu Soricut, and Vittorio Ferrari
Connecting Vision and Language with Video Localized Narratives
IEEE Computer Vision and Pattern Recognition (CVPR), 2023. (Highlight)
Berk Kaya, Suryansh Kumar, Carlos Oliveira, Vittorio Ferrari, Luc Van Gool
Multi-View Photometric Stereo Revisited
Winter Conference on Applications of Computer Vision (WACV), 2023
2022
Rodrigo Benenson, Vittorio Ferrari
From couloring-in to pointillism: revisiting semantic segmentation supervision
arXiv, November 2022.
Data released as part of Open Images V7
Michał J. Tyszkiewicz, Kevis-Kokitsi Maninis, Stefan Popov, Vittorio Ferrari
European Conference on Computer Vision (ECCV), 2022.
Jasper Uijlings, Thomas Mensink, Vittorio Ferrari
The Missing Link: Finding label relations across datasets
European Conference on Computer Vision (ECCV), 2022.
Andrea Agostinelli, Michal Pándy, Jasper Uijlings, Thomas Mensink, Vittorio Ferrari
How stable are Transferability Metrics evaluations?
European Conference on Computer Vision (ECCV), 2022
Konstantinos Rematas, Andrew Liu, Pratul P. Srinivasan, Jonathan T. Barron, Andrea Tagliasacchi, Tom Funkhouser, Vittorio Ferrari
IEEE Computer Vision and Pattern Recognition (CVPR), 2022
Andrea Agostinelli, Jasper Uijlings, Thomas Mensink, Vittorio Ferrari
Transferability Metrics for Selecting Source Model Ensembles
IEEE Computer Vision and Pattern Recognition (CVPR), 2022 (oral)
Michal Pándy, Andrea Agostinelli, Jasper Uijlings, Vittorio Ferrari, Thomas Mensink
Transferability Estimation using Bhattacharyya Class Separability
IEEE Computer Vision and Pattern Recognition (CVPR), 2022
Denys Rozumnyi, Martin R. Oswald, Vittorio Ferrari, Marc Pollefeys
Motion-from-Blur: 3D Shape and Motion Estimation of Motion-blurred Objects in Videos
IEEE Computer Vision and Pattern Recognition (CVPR), 2022
Berk Kaya, Suryansh Kumar, Carlos Oliveira, Vittorio Ferrari, Luc Van Gool
Uncertainty-Aware Deep Multi-View Photometric Stereo
IEEE Computer Vision and Pattern Recognition (CVPR), 2022
Kevis-Kokitsi Maninis*, Stefan Popov*, Matthias Nießner, Vittorio Ferrari
Vid2CAD: CAD Model Alignment using Multi-View Constraints from Videos
IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2022
(on arXiv since December 2020, latest version January 2022)
Thomas Mensink, Jasper Uijlings, Alina Kuznetsova, Michael Gygli, Vittorio Ferrari
Factors of Influence for Transfer Learning across Diverse Appearance Domains and Task Types
IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2022
(on arXiv since March 2021, latest version November 2021)
Berk Kaya, Suryansh Kumar, Francesco Sarno, Vittorio Ferrari, Luc Van Gool
Neural Radiance Fields Approach to Deep Multi-View Photometric Stereo
Winter Conference on Applications of Computer Vision (WACV), 2022.
Francesco Sarno, Suryansh Kumar, Berk Kaya, Zhiwu Huang, Vittorio Ferrari, Luc Van Gool
Neural Architecture Search for Efficient Uncalibrated Deep Photometric Stereo
Winter Conference on Applications of Computer Vision (WACV), 2022.
2021
Zhaohui Yang, Miaojing Shi, Yannis Avrithis, Chao Xu, Vittorio Ferrari
Training Object Detectors from Few Weakly-Labeled and Many Unlabeled Images
Pattern Recognition, Vol. 120 (Dec. 2021)
Denys Rozumnyi, Martin Oswald, Vittorio Ferrari, Marc Pollefeys
Shape from Blur: Recovering Textured 3D Shape and Motion of Fast Moving Objects
Conference on Neural Information Processing Systems (NeurIPS), 2021
Soravit Changpinyo, Jordi Pont-Tuset, Vittorio Ferrari, and Radu Soricut
International Conference on Computer Vision (ICCV), 2021
Konstantinos Rematas, Ricardo Martin-Brualla, Vittorio Ferrari
ShaRF: Shape-conditioned Radiance Fields from a Single View
Project website
International Conference on Machine Learning (ICML), 2021
Candice Schumann, Susanna Ricco, Utsav Prabhu, Vittorio Ferrari, Caroline Pantofaru
A Step Toward More Inclusive People Annotations for Fairness
AAAI/ACM Conference on Artificial Intelligence, Ethics, and Society (AIES), 2021
Francis Engelmann, Konstantinos Rematas, Bastian Leibe, Vittorio Ferrari
From Points to Multi-Object 3D Reconstruction
IEEE Computer Vision and Pattern Recognition (CVPR), 2021
Denys Rozumnyi, Martin Oswal, Vittorio Ferrari, Jirı Matas, Marc Pollefeys
DeFMO: Deblurring and Shape Recovery of Fast Moving Objects
IEEE Computer Vision and Pattern Recognition (CVPR), 2021
Berk Kaya, Suryansh Kumar, Carlos Oliveira, Vittorio Ferrari, Luc Van Gool
Uncalibrated Neural Inverse Rendering for Photometric Stereo of General Surfaces
IEEE Computer Vision and Pattern Recognition (CVPR), 2021
Michael Gygli, Jasper Uijlings, and Vittorio Ferrari
Towards reusable network components by learning compatible representations
AAAI Conference on Artificial Intelligence (AAAI), 2021.
Alina Kuznetsova, Aakrati Talati, Yiwen Luo, Keith Simmons, Vittorio Ferrari
Efficient video annotation with visual interpolation and frame selection guidance
Winter Conference on Applications of Computer Vision (WACV), 2021.
Presentation video
2020
Jasper R. R. Uijlings, Mykhayloa Andriluka, and Vittorio Ferrari
Panoptic Image Annotation with a Collaborative Assistant
ACM Multimedia (ACM MM), 2020
Jordi Pont-Tuset, Jasper Uijlings, Soravit Changpinyo, Radu Soricut, and Vittorio Ferrari
Connecting Vision and Language with Localized Narratives
European Conference on Computer Vision (ECCV), 2020. (Spotlight)
Stefan Popov, Pablo Bauszat, Vittorio Ferrari
CoReNet: Coherent 3D scene reconstruction from a single RGB image
European Conference on Computer Vision (ECCV), 2020. (oral)
See also supplementary material.
Theodora Kontogianni*, Michael Gygli*, Jasper Uijlings and Vittorio Ferrari
Continuous Adaptation for Interactive Object Segmentation by Learning from Corrections
European Conference on Computer Vision (ECCV), 2020.
Mykhayloa Andriluka, Stefano Pellegrini, Stefan Popov and Vittorio Ferrari
Efficient Full Image Interactive Segmentation by Leveraging Within-image Appearance Similarity
arXiv, July 2020
Albert Pumarola, Stefan Popov, Francesc Moreno-Noguer, and Vittorio Ferrari
C-Flow: Conditional Generative Flow Models for Images and 3D Point Clouds
IEEE Computer Vision and Pattern Recognition (CVPR), 2020
Konstantinos Rematas and Vittorio Ferrari
Neural Voxel Renderer: Learning an Accurate and Controllable Rendering Tool
IEEE Computer Vision and Pattern Recognition (CVPR), 2020
Project page, code on github
Alina Kuznetsova, Hassan Rom, Neil Alldrin, Jasper Uijlings, Ivan Krasin, Jordi Pont-Tuset, Shahab Kamali, Stefan Popov, Matteo Malloci, Tom Duerig and Vittorio Ferrari
International Journal of Computer Vision (IJCV), 128(7), pp. 1956-1981, 2020
Michael Gygli and Vittorio Ferrari
Efficient Object Annotation via Speaking and Pointing
International Journal of Computer Vision (IJCV), 128(5), pp. 1061-1075, May 2020
Paul Henderson and Vittorio Ferrari
Learning single-image 3D reconstruction by generative modelling of shape, pose and shading
International Journal of Computer Vision (IJCV), 128(4), pp. 835-854, April 2020
Code for our differentiable renderer (DIRT)
2019
Jordi Pont-Tuset, Michael Gygli, and Vittorio Ferrari
Natural Vocabulary Emerges from Free-Form Annotations
ArXiv, June 2019
A. Kolesnikov, A. Kuznetsova, C.H. Lampert, and V. Ferrari
Detecting Visual Relationships Using Box Attention (full ArXiv verison)
ICCV Workshop on Scene Graph Representation and Learning (ICCVW), 2019
Eirikur Agustsson, Jasper Uijlings, and Vittorio Ferrari
Interactive Full Image Segmentation by Considering All Regions Jointly
IEEE Computer Vision and Pattern Recognition (CVPR), 2019
Michael Gygli and Vittorio Ferrari
Fast Object Class Labelling via Speech
IEEE Computer Vision and Pattern Recognition (CVPR), 2019
Rodrigo Benenson, Stefan Popov, and Vittorio Ferrari
Large-scale interactive object segmentation with human annotators
IEEE Computer Vision and Pattern Recognition (CVPR), 2019
Zbigniew Wojna, Vittorio Ferrari, Sergio Guadarrama, Nathan Silberman, Liang-Chieh Chen, Alireza Fathi, and Jasper Uijlings
The Devil is in the Decoder: Classification, Regression and GANs
International Journal of Computer Vision (IJCV), 127(11-12), pp. 1694-1706, December 2019
2018
M. Andriluka, J.R.R. Uijlings, and V. Ferrari
Fluid Annotation: a human-machine collaboration interface for full image annotation
ACM MultiMedia (ACMMM), 2018 (oral)
See also the demo and the Google AI Research blogpost
Paul Henderson and Vittorio Ferrari
Learning to Generate and Reconstruct 3D Meshes with only 2D Supervision
British Machine Vision Conference (BMVC), 2018. (oral)
K. Konyushkova, J.R.R. Uijlings, C.H. Lampert, and V. Ferrari
Learning Intelligent Dialogs for Bounding Box Annotation
IEEE Computer Vision and Pattern Recognition (CVPR), 2018 (spotlight oral)
Recording of spotlight (starts at 01:07:50)
J. R. R. Uijlings, S. Popov and V. Ferrari
Revisiting knowledge transfer for training object class detectors
IEEE Computer Vision and Pattern Recognition (CVPR), 2018
H. Caesar, J.R.R. Uijlings, and Vittorio Ferrari
COCO-Stuff: Thing and Stuff Classes in Context
IEEE Computer Vision and Pattern Recognition (CVPR), June 2018
2017
Z. Wojna, V. Ferrari, S. Guadarrama, N. Silberman, L.-C. Chen, A. Fathi and J.R.R. Uijlings
British Machine Vision Conference (BMVC), 2017. (spotlight oral)
D. P. Papadopoulos, J.R.R. Uijlings, F. Keller and V. Ferrari
Extreme clicking for efficient object annotation
International Conference on Computer Vision (ICCV), 2017
D. P. Papadopoulos, J. R. R. Uijlings, F. Keller and V. Ferrari
Training object class detectors with click supervision
IEEE Computer Vision and Pattern Recognition (CVPR), 2017. (spotlight oral)