Recent Submissions

  • Safari from visual signals: recovering volumetric 3d shapes 

    Agudo Martínez, Antonio (Institute of Electrical and Electronics Engineers (IEEE), 2022)
    Conference report
    Open Access
    In this paper we propose a convex approach for recovering a detailed 3D volumetric geometry of several objects from visual signals. To this end, we first present a minimal detailed surface energy that is optimized together ...
  • An adaptable approach to learn realistic legged locomotion without examples 

    Ordonez-Apraez, Daniel; Agudo Martínez, Antonio; Moreno-Noguer, Francesc; Martín Muñoz, Mario (2022)
    Conference report
    Open Access
    Learning controllers that reproduce legged locomotion in nature has been a long-time goal in robotics and computer graphics. While yielding promising results, recent approaches are not yet flexible enough to be applicable ...
  • Matching and recovering 3D people from multiple views 

    Pérez Yus, Alejandro; Agudo Martínez, Antonio (Institute of Electrical and Electronics Engineers (IEEE), 2022)
    Conference report
    Open Access
    This paper introduces an approach to simultaneously match and recover 3D people from multiple calibrated cameras. To this end, we present an affinity measure between 2D detections across different views that enforces an ...
  • Knowledge representation for explainability in collaborative robotics and adaptation 

    Olivares Alarcos, Alberto; Foix Salmerón, Sergi; Alenyà Ribas, Guillem (CEUR-WS.org, 2021)
    Conference report
    Open Access
    Autonomous robots are going to be used in a large diversity of contexts, interacting and/or collaborating with humans, who will add uncertainty to the collaborations and cause re-planning and adaptations to the execution ...
  • Learning grounded word meaning representations on similarity graphs 

    Dimiccoli, Mariella; Wendt, Herwig; Battle, Pau (PUBLICACIONS EUPBL, ETT-ST/ACLSI/P99/EP2.1, 2021)
    Conference report
    Open Access
    This paper introduces a novel approach to learn visually grounded meaning representations of words as low-dimensional node embeddings on an underlying graph hierarchy. The lower level of the hierarchy models modality-specific ...
  • Self-supervised policy adaptation during deployment 

    Hansen, Nicklas; Jangir, Rishabh; Alenyà Ribas, Guillem; Abbeel, Pieter; Efros A, Alexei; Pinto, Lerrel; Wang, Xiaolong (OpenReview.net, 2021)
    Conference report
    Open Access
    In most real world scenarios, a policy trained by reinforcement learning in one environment needs to be deployed in another, potentially quite different environment. However, generalization across different environments ...
  • PhysXNet: a customizable approach for learning cloth dynamics on dressed people 

    Sánchez Riera, Jordi; Pumarola Peris, Albert; Moreno-Noguer, Francesc (Institute of Electrical and Electronics Engineers (IEEE), 2021)
    Conference report
    Open Access
    We introduce PhysXNet, a learning-based approach to predict the dynamics of deformable clothes given 3D skeleton motion sequences of humans wearing these clothes. The proposed model is adaptable to a large variety of ...
  • SIDER: Single-Image Neural Optimization for Facial Geometric Detail Recovery 

    Chatziagapi, Aggelina; Athar, ShahRukh; Moreno-Noguer, Francesc; Samaras, Dimitris (Institute of Electrical and Electronics Engineers (IEEE), 2021)
    Conference report
    Open Access
    We present SIDER (Single-Image neural optimization for facial geometric DEtail Recovery), a novel photometric optimization method that recovers detailed facial geometry from a single image in an unsupervised manner. Inspired ...
  • Body size and depth disambiguation in multi-person reconstruction from single images 

    Ugrinovic Kehdy, Nicolas; Ruiz Ovejero, Adrià; Agudo Martínez, Antonio; Sanfeliu Cortés, Alberto; Moreno-Noguer, Francesc (Institute of Electrical and Electronics Engineers (IEEE), 2021)
    Conference report
    Open Access
    We address the problem of multi-person 3D body pose and shape estimation from a single image. While this problem can be addressed by applying single-person approaches multiple times for the same scene, recent works have ...
  • PI-Net: Pose Interacting Network for Multi-Person Monocular 3D Pose Estimation 

    Guo, Wen; Corona Puyane, Enric; Moreno-Noguer, Francesc; Alameda-Pineda, Xavier (Institute of Electrical and Electronics Engineers (IEEE), 2021)
    Conference report
    Open Access
    Recent literature addressed the monocular 3D pose estimation task very satisfactorily. In these studies, different persons are usually treated as independent pose instances to estimate. However, in many every-day situations, ...
  • Human to robot whole-body motion transfer 

    Arduengo García, Miguel; Arduengo Garcia, Ana; Colomé Figueras, Adrià; Lobo Prat, Joan; Torras, Carme (Institute of Electrical and Electronics Engineers (IEEE), 2021)
    Conference report
    Open Access
    Transferring human motion to a mobile robotic manipulator and ensuring safe physical human-robot interaction are crucial steps towards automating complex manipulation tasks in human-shared environments. In this work, we ...
  • SMPLicit: Topology-aware generative model for clothed people 

    Corona Puyane, Enric; Pumarola Peris, Albert; Alenyà Ribas, Guillem; Pons-Moll, Gerard; Moreno-Noguer, Francesc (Institute of Electrical and Electronics Engineers (IEEE), 2021)
    Conference report
    Open Access
    In this paper we introduce SMPLicit, a novel generative model to jointly represent body pose, shape and clothing geometry. In contrast to existing learning-based approaches that require training specific models for each ...

View more