Research

1. Martín Méndez-López, Alicia Fornés and Antonio Agudo
   Recovering and Classifying Upper Limb Impairment Trajectories after Stroke [draft]
   IEEE International Conference on Image Processing (ICIP), Anchorage (Alaska, USA), 2025.
2. Marc Gutiérrez-Pérez and Antonio Agudo
   SoccerNet-v3D: Leveraging Sports Broadcast Replays for 3D Scene Understanding [draft]
   IEEE International Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), Nashville (Tennessee, USA), 2025.
   
3. Guillem Capellera, Antonio Rubio, Luiz Ferraz and Antonio Agudo
   Unified Uncertainty-Aware Diffusion for Multi-Agent Trajectory Modeling [draft] [supp]
   IEEE International Conference on Computer Vision and Pattern Recognition (CVPR), Nashville (Tennessee, USA), 2025.
   
4. Shubh Singhai, Raül Pérez-Gonzalo, Andreas Espersen and Antonio Agudo
   Dual-space Augmented Intrinsic-LORA for Wind Turbine Segmentation [draft]
   IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), Hyderabad (India), 2025.
5. Marc Peral, Guillem Capellera, Antonio Rubio, Luiz Ferraz, Francesc Moreno-Noguer and Antonio Agudo
   Temporally Accurate Events Detection Through Ball Possessor Recognition in Soccer [draft]
   International conference on Computer Vision Theory and Applications (VISAPP), Porto (Portugal), 2025.
6. Sergio M. de Paco and Antonio Agudo
   4DPV: 4D Pet from Videos by Coarse-to-Fine Non-Rigid Radiance Fields [draft]
   Asian Conference on Computer Vision (ACCV), Hanoi (Vietnam), 2024.
7. Guillem Capellera, Luiz Ferraz, Antonio Rubio, Antonio Agudo and Francesc Moreno-Noguer
   TranSPORTmer: A Holistic Approach to Trajectory Understanding in Multi-Agent Sports Scenarios [draft]
   Asian Conference on Computer Vision (ACCV), Hanoi (Vietnam), 2024.
8. Daniel Ordoñez, Giulio Turrisi, Vladimir Kostic, Mario Martin, Antonio Agudo, Francesc Moreno-Noguer, Massimiliano Pontil, Claudio Semini and Carlos Mastalli
   Morphological Symmetries in Robotics [draft]
   International Journal of Robotics Research (IJR), 2024, to appear.
9. Marc Pérez, Antonio Agudo, Gijs Dubbelman and Pavol Jancura
   Class Prototypical Loss for Enhanced Feature Separation in 3D Object Detection [draft]
   IEEE International Conference on Intelligent Transportation Systems (ITSC), Edmonton (Canada), 2024.
10. Raül Pérez-Gonzalo, Andreas Espersen and Antonio Agudo
    Generalized Nested Latent Variables Models for lossy Coding Applied to Wind Turbine Scenarios [draft]
    IEEE International Conference on Image Processing (ICIP), Abu Dhabi (United Arab Emirates), 2024.
11. Guillem Capellera, Luiz Ferraz, Antonio Rubio, Antonio Agudo and Francesc Moreno-Noguer
    FootBots: A transformer-based Architecture for Motion Prediction in Soccer [draft]
    IEEE International Conference on Image Processing (ICIP), Abu Dhabi (United Arab Emirates), 2024.
12. Alejandro Casanova and Antonio Agudo
    Uncalibrated and Unsupervised Photometric Stereo with Piecewise Regularizer [draft]
    IEEE International Conference on Image Processing (ICIP), Abu Dhabi (United Arab Emirates), 2024.
13. Guénolé Fiche, Simon Leglaive, Xavier Alameda-Pineda, Antonio Agudo and Francesc Moreno-Noguer
    VQ-HPS: Human Pose and Shape Estimation in a Vector-Quantized Latent Space [draft]
    European Conference on Computer Vision (ECCV), Milano (Italy), 2024.
    
14. Marc Gutiérrez-Pérez and Antonio Agudo
    No Bells, Just Whistles: Sports Field Registration by Leveraging Geometric Properties [draft]
    IEEE International Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), Seattle (Washington, USA), 2024.
    
15. Arne Berresheim and Antonio Agudo
    Photovoltaic Power Forecasting using Sky images and Sun Motion [draft]
    IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), Seoul (Korea), 2024.
16. Nicolas Ugrinovic, Adria Ruiz, Antonio Agudo, Alberto Sanfeliu and Francesc Moreno-Noguer
    PIRO: Permutation-Invariant Relational Network for Multi-person 3D Pose Estimation [draft]
    International conference on Computer Vision Theory and Applications (VISAPP), Rome (Italy), 2024.
17. Marc Pérez and Antonio Agudo
    Robust Multimodal and Multi-Object Tracking for Autonomous Driving Applications [draft]
    IEEE International Conference on Advanced Robotics (ICAR), Abu Dhabi (United Arab Emirates), 2023.
18. Raül Pérez-Gonzalo, Andreas Espersen and Antonio Agudo
    Robust Wind Turbine Blade Segmentation from RGB Images in the Wild [draft]
    IEEE International Conference on Image Processing (ICIP), Kuala Lumpur (Malaysia), 2023.
19. Ana Urdapilleta and Antonio Agudo
    Comparative study of feature localization methods for endoscopy image matching [draft]
    IEEE International Conference on Image Processing Workshops (ICIPW), Kuala Lumpur (Malaysia), 2023.
20. Daniel Ordoñez, Mario Martin, Antonio Agudo and Francesc Moreno-Noguer
    Morphological symmetries in robot learning [draft]
    RSS Workshop on Symmetries in Robot Learning (RSSW), Daegu (Korea), 2023.
21. Daniel Ordoñez, Mario Martin, Antonio Agudo and Francesc Moreno-Noguer
    On discrete symmetries of robotics systems: A group-theoretic and data-driven analysis [draft]
    Robotics: Science and Systems Conference (RSS), Daegu (Korea), 2023.
22. Antonio Agudo
    Detail-aware Uncalibrated Photometric Stereo [draft]
    IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), Rodos (Greece), 2023.
23. Ruijie Ren, Mohit Gurnani, Jordi Sánchez-Riera, Adrian López, Fan Zhang, Yurun Tian, Guillem Alenyà, Antonio Agudo, Yiannis Demirism, Krystian Mikolajczyk and Francesc Moreno-Noguer
    Grasp-Oriented Fine-grained Cloth Segmentation without Real Supervision [draft]
    IEEE International Conference on Machine Vision and Applications (ICMVA), Singapore, 2023.
24. Jianxiong Shen, Antonio Agudo, Francesc Moreno-Noguer and Adria Ruiz
    Conditional-Flow NeRF: Accurate 3D Modelling with Reliable Uncertainty Quantification [draft]
    European Conference on Computer Vision (ECCV), Tel Aviv (Israel), 2022.
    
25. Antonio Agudo
    Spline Human Motion Recovery [draft]
    IEEE International Conference on Image Processing (ICIP), Bordeaux (France), 2022.
26. Pablo Estevez and Antonio Agudo
    Uncalibrated, Unified and Unsupervised Specular-aware Photometric Stereo [draft]
    International Conference on Pattern Recognition Workshops (ICPR), Montreal (Canada), 2022.
27. Daniel Ordoñez, Antonio Agudo, Francesc Moreno-Noguer and Mario Martin
    An Adaptable Approach to Learn Realistic Legged Locomotion without Examples [draft]
    IEEE International Conference on Robotics and Automation (ICRA), Philadelphia (Pennsylvania, USA), 2022.
28. Antonio Agudo
    Safari from Visual Signals: Recovering Volumetric 3D Shapes [draft]
    IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), Singapore, 2022.
29. Alejandro Perez-Yus and Antonio Agudo
    Matching and Recovering 3D People from Multiple Views [draft] [video]
    IEEE Winter Conference on Applications of Computer Vision (WACV), Waikoloa (Hawaii, USA), 2022.
30. Adria Ruiz, Antonio Agudo and Francesc Moreno-Noguer
    Generating Attribution Maps with Disentangled Masked Backpropagation [draft]
    IEEE International Conference on Computer Vision (ICCV), Virtual, 2021.
    
31. Jianxiong Shen, Adria Ruiz, Antonio Agudo and Francesc Moreno-Noguer
    Stochastic Neural Radiance Fields: Quantifying Uncertainty in Implicit 3D Representations [draft]
    IEEE International Conference on 3D Vision (3DV), London (United Kingdom), 2021.
    
32. Nicolas Ugrinovic, Adria Ruiz, Antonio Agudo, Alberto Sanfeliu and Francesc Moreno-Noguer
    Body Size and Depth Disambiguation in Multi-Person Reconstruction from Single Images [draft]
    IEEE International Conference on 3D Vision (3DV), London (United Kingdom), 2021.
    
33. Antonio Agudo, Vincent Lepetit and Francesc Moreno-Noguer
    Simultaneous Completion and Spatio-Temporal Grouping of Corrupted Motion Tracks [draft]
    The Visual Computer (TVC), 38(11): 3937-3952, 2022.
34. Antonio Agudo
    Piecewise Bézier Space: Recovering 3D Dynamic Motion from Video [draft]
    IEEE International Conference on Image Processing (ICIP), Anchorage (Alaska, USA), 2021.
35. Alexander Vakhitov, Luis Ferraz, Antonio Agudo and Francesc Moreno-Noguer
    Uncertainty-Aware Camera Pose Estimation from Points and Lines [draft]
    IEEE International Conference on Computer Vision and Pattern Recognition (CVPR), Virtual, 2021.
    
36. Antonio Agudo [poster]
    Total Estimation from RGB Video: On-line Camera Self-Calibration, Non-Rigid Shape and Motion [draft]
    IEEE International Conference on Pattern Recognition (ICPR), Milan (Italy), 2020.
37. Javier Garcia-Lopez, Antonio Agudo and Francesc Moreno-Noguer
    E-DNAS: Differentiable Neural Architecture Search for Embedded Systems [draft]
    IEEE International Conference on Pattern Recognition (ICPR), Milan (Italy), 2020.
38. Antonio Agudo
    Unsupervised 3D Reconstruction and Grouping of Rigid and Non-Rigid Categories [draft]
    IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 44(1): 519-532, 2022.
39. Vikramjit Sidhu, Edgar Tretschk, Vladislav Golyanik, Antonio Agudo and Christian Theobalt
    Neural Dense Non-Rigid Structure from Motion with Latent Space Constraints [draft] [supp] [video]
    European Conference on Computer Vision (ECCV), Glasgow (United Kingdom), 2020.
    
40. Antonio Agudo
    Segmentation and 3D Reconstruction of Non-Rigid Shape from RGB Video [draft]
    IEEE International Conference on Image Processing (ICIP), Abu Dhabi (United Arab Emirates), 2020.
41. Albert Pumarola, Antonio Agudo, Aleix M. Martinez, Alberto Sanfeliu and Francesc Moreno-Noguer
    GANimation: One-Shot Anatomically Consistent Facial Animation [draft]
    International Journal of Computer Vision (IJCV), 128(3):698-713, 2020.
42. Gemma Rotger, Francesc Moreno-Noguer, Felipe Lumbreras and Antonio Agudo
    Single View Facial Hair 3D Reconstruction [draft]
    Iberian Conference on Pattern Recognition and Image Analysis, Madrid (Spain), 2019.
43. Gemma Rotger, Francesc Moreno-Noguer, Felipe Lumbreras and Antonio Agudo
    Detailed 3D Face Reconstruction from a Single RGB Image [draft]
    International Conference in Central Europe on Computer Graphics, Visualization and Computer Vision, Plzen (Czech Republic), 2019.
44. Antonio Agudo and Francesc Moreno-Noguer
    Shape Basis Interpretation for Monocular Deformable 3D Reconstruction [draft]
    IEEE Transactions on Multimedia (TMM) 21(4):821-834, 2019.
45. Albert Pumarola, Antonio Agudo, Aleix M. Martinez, Alberto Sanfeliu and Francesc Moreno-Noguer
    GANimation: Anatomically-aware Facial Animation from a Single Image [draft]
    European Conference on Computer Vision (ECCV), Munich (Germany), 2018.
    Best Paper Award Honorable Mention
46. Antonio Agudo and Francesc Moreno-Noguer
    Deformable Motion 3D Reconstruction by Union of Regularized Subspaces [draft]
    IEEE International Conference on Image Processing (ICIP), Athens (Greece), 2018.
47. Gemma Rotger, Felipe Lumbreras, Francesc Moreno-Noguer and Antonio Agudo
    2D-to-3D Facial Expression Transfer [draft]
    IEEE International Conference on Pattern Recognition (ICPR), Beijing (China), 2018.
48. Antonio Agudo and Francesc Moreno-Noguer
    Robust Spatio-Temporal Clustering and Reconstruction of Multiple Deformable Bodies [draft]
    IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI) 41(4):971-984, 2019.
49. Albert Pumarola, Antonio Agudo, Alberto Sanfeliu and Francesc Moreno-Noguer
    Unsupervised Person Image Synthesis in Arbitrary Poses [draft]
    IEEE International Conference on Computer Vision and Pattern Recognition (CVPR), Salt Lake City (Utah, USA), 2018.
50. Antonio Agudo, Melcior Pijoan and Francesc Moreno-Noguer [poster]
    Image Collection Pop-up: 3D Reconstruction and Clustering of Rigid and Non-Rigid Categories [draft]
    IEEE International Conference on Computer Vision and Pattern Recognition (CVPR), Salt Lake City (Utah, USA), 2018.
51. Albert Pumarola, Antonio Agudo, Lorenzo Porzi, Alberto Sanfeliu, Vicent Lepetit and Francesc Moreno-Noguer
    Geometry-Aware Network for Non-Rigid Shape Prediction from a Single View [draft]
    IEEE International Conference on Computer Vision and Pattern Recognition (CVPR), Salt Lake City (Utah, USA), 2018.
52. Antonio Agudo and Francesc Moreno-Noguer
    A Scalable, Efficient, and Accurate Solution to Non-Rigid Structure from Motion [draft] [bibtex]
    Computer Vision and Image Understanding (CVIU), 167(2): 121-133, 2018.
53. Antonio Agudo and Francesc Moreno-Noguer
    Force-based Representation for Non-Rigid Shape and Elastic Model Estimation [draft] [bibtex] [code]
    IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 40(9):2137-2150, 2018.
54. Antonio Agudo and Francesc Moreno-Noguer [poster]
    DUST: Dual Union of Spatio-Temporal Subspaces for Monocular Multiple Object 3D Reconstruction [draft]
    IEEE International Conference on Computer Vision and Pattern Recognition (CVPR), Honolulu (Hawaii, USA), 2017.
55. Albert Pumarola, Alexander Vakhitov, Antonio Agudo, Alberto Sanfeliu and Francesc Moreno-Noguer
    PL-SLAM: Real-Time Monocular Visual SLAM with Points and Lines [draft]
    IEEE International Conference on Robotics and Automation (ICRA), Singapore, 2017.
56. Antonio Agudo and Francesc Moreno-Noguer
    Global Model with Local Interpretation for Dynamic Shape Reconstruction [draft]
    IEEE Winter Conference on Applications of Computer Vision (WACV), Santa Rosa (California, USA), 2017.
57. Antonio Agudo and Francesc Moreno-Noguer
    Combining Local-Physical and Global-Statistical Models for Sequential Deformable Shape from Motion [draft] [bibtex]
    International Journal of Computer Vision (IJCV), 122(2):371-387, 2017.
58. Antonio Agudo and Francesc Moreno-Noguer
    Recovering Pose and 3D Deformable Shape from Multi-Instance Image Ensembles [draft] [bibtex]
    Asian Conference on Computer Vision (ACCV), Taipei (Taiwan), 2016.
59. Antonio Agudo, J. M. M. Montiel, Lourdes Agapito and Begoña Calvo
    Modal Space: A Physics-Based Model for Sequential Estimation of Time-Varying Shape from Monocular Video
    Journal of Mathematical Imaging and Vision (JMIV), 57(1):75-98, 2017. [bibtex] [draft]
60. Antonio Agudo, Francesc Moreno-Noguer, Begoña Calvo and J. M. M. Montiel
    Real-Time 3D Reconstruction of Non-Rigid Shapes with a Single Moving Camera [draft] [bibtex]
    Computer Vision and Image Understanding (CVIU), 153(12):37-54, 2016.
61. Antonio Agudo, J. M. M. Montiel, Begoña Calvo and Francesc Moreno-Noguer
    Mode-Shape Interpretation: Re-Thinking Modal Space for Recovering Deformable Shapes [draft] [bibtex]
    IEEE Winter Conference on Applications of Computer Vision (WACV), Lake Placid (New York, USA), 2016.
62. Antonio Agudo and Francesc Moreno-Noguer [poster]
    Learning Shape, Motion and Elastic Models in Force Space [draft] [bibtex] [video]
    IEEE International Conference on Computer Vision (ICCV), Santiago (Chile), 2015.
63. Antonio Agudo, Francesc Moreno-Noguer, Begoña Calvo and J. M. M. Montiel
    Sequential Non-Rigid Structure from Motion using Physical Priors [draft] [bibtex]
    IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI) 38(5):979-994, 2016.
64. Antonio Agudo and Francesc Moreno-Noguer [poster]
    Simultaneous Pose and Non-Rigid Shape with Particle Dynamics [draft] [bibtex] [video]
    IEEE International Conference on Computer Vision and Pattern Recognition (CVPR), Boston (Massachusetts, USA), 2015.
65. Antonio Agudo, J. M. M. Montiel, Lourdes Agapito and Begoña Calvo [poster]
    Online Dense Non-Rigid 3D Shape and Camera Motion Recovery [draft] [bibtex] [video]
    British Machine Vision Conference (BMVC), Nottingham (United Kingdom), 2014.
66. Antonio Agudo, Lourdes Agapito, Begoña Calvo and J. M. M. Montiel [poster]
    Good Vibrations: A Modal Analysis Approach for Sequential Non-Rigid Structure from Motion [draft] [bibtex] [video]
    IEEE International Conference on Computer Vision and Pattern Recognition (CVPR), Columbus (Ohio, USA), 2014.
67. Antonio Agudo, Begoña Calvo and J. M. M. Montiel
    3D Reconstruction of Non-Rigid Surfaces in Real-Time using Wedge Elements [draft] [bibtex] [StrongDeformation] [RealTime]
    5th Workshop on Non-Rigid Shape Analysis and Deformable Image Alignment NORDIA (ECCV 2012), Florence (Italy), 2012.
68. Antonio Agudo, Begoña Calvo and J. M. M. Montiel [poster]
    Finite Element based Sequential Bayesian Non-Rigid Structure from Motion [draft] [bibtex] [silicone] [PaperBending] [FlagPaper]
    IEEE International Conference on Computer Vision and Pattern Recognition (CVPR), Providence (Rhode Island, USA), 2012.
69. Antonio Agudo, Begoña Calvo and J. M. M. Montiel
    FEM Models to Code Non-Rigid EKF Monocular SLAM [draft] [bibtex] [video] [YouTube]
    1st IEEE International Workshop on Dynamic Shape Capture and Analysis 4DMOD (ICCV 2011), Barcelona (Spain), 2011.
70. Antonio Agudo
    Sequential Bayesian Non-Rigid Structure from Motion [draft]
    PhD Thesis, University of Zaragoza (Spain), 2015.