RoboTHOR: An Open Simulation-to-Real Embodied AI Platform
- Matt Deitke, Winson Han, Ali Farhadi
- Computer ScienceComputer Vision and Pattern Recognition
- 14 April 2020
RoboTHOR offers a framework of simulated environments paired with physical counterparts to systematically explore and overcome the challenges of simulation-to-real transfer, and a platform where researchers across the globe can remotely test their embodied models in the physical world.
Naive Bayes Super-Resolution Forest
- Jordi Salvador, Eduardo Pérez-Pellitero
- Computer ScienceIEEE International Conference on Computer Vision
- 7 December 2015
A bimodal tree for clustering, which successfully exploits the antipodal invariance of the coarse-to-high-res mapping of natural image patches and provides scalability to finer partitions of the underlying coarse patch space, is presented.
Non-Parametric Blur Map Regression for Depth of Field Extension
- Laurent D'Andres, Jordi Salvador, Axel Kochale, S. Süsstrunk
- Computer ScienceIEEE Transactions on Image Processing
- 1 April 2016
This paper presents a blind deblurring pipeline able to restore real camera systems by slightly extending their DOF and recovering sharpness in regions slightly out of focus by relying first on the estimation of the spatially varying defocus blur.
PSyCo: Manifold Span Reduction for Super Resolution
- Eduardo Pérez-Pellitero, Jordi Salvador, Javier Ruiz-Hidalgo, B. Rosenhahn
- Computer ScienceComputer Vision and Pattern Recognition
- 27 June 2016
A novel regression-based SR algorithm that benefits from an extended knowledge of the structure of both manifolds, and proposes a transform that collapses the 16 variations induced from the dihedral group of transforms and antipodality into a single primitive.
AllenAct: A Framework for Embodied AI Research
- Luca Weihs, Jordi Salvador, Aniruddha Kembhavi
- Computer ScienceArXiv
- 28 August 2020
AllenAct is introduced, a modular and flexible learning framework designed with a focus on the unique requirements of Embodied AI research that provides first-class support for a growing collection of embodied environments, tasks and algorithms.
Image-based multi-view scene analysis using 'conexels'
- J. Casas, Jordi Salvador
- Computer Science
- 1 November 2006
A 3D geometry is proposed for multi-view scene analysis providing a better balance in terms of the number of pixels used to analyse each elementary volumetric unit, which is non-regular in 3D space, but becomes regular once projected onto camera images, adapting the sampling to the images.
Antipodally Invariant Metrics for Fast Regression-Based Super-Resolution
- Eduardo Pérez-Pellitero, Jordi Salvador, Javier Ruiz-Hidalgo, B. Rosenhahn
- Computer ScienceIEEE Transactions on Image Processing
- 1 June 2016
This paper presents a very fast regression-based algorithm, which builds on the densely populated anchored neighborhoods and sublinear search structures, and proposes a simple yet effective antipodally invariant transform that can be easily included in the Euclidean distance calculation.
ProcTHOR: Large-Scale Embodied AI Using Procedural Generation
- Matt Deitke, Eli VanderBilt, Roozbeh Mottaghi
- Computer ScienceArXiv
- 14 June 2022
The proposed PROCTHOR, a framework for procedural generation of Embodied AI environments, enables us to sample arbitrarily large datasets of diverse, interactive, customizable, and performant virtual environments to train and evaluate embodied agents across navigation, interaction, and manipulation tasks.
Multi-person Tracking Strategies Based on Voxel Analysis
- C. Canton-Ferrer, Jordi Salvador, J. Casas, M. Pardàs
- Computer ScienceCLEaR
- 2007
Two approaches to the problem of simultaneous tracking of several people in low resolution sequences from multiple calibrated cameras are presented and a particle filtering scheme adapted to the incoming 3D discrete data is proposed.
Learning About Objects by Learning to Interact with Them
- Martin Lohmann, Jordi Salvador, Aniruddha Kembhavi, Roozbeh Mottaghi
- Computer ScienceNeural Information Processing Systems
- 1 June 2020
This work presents a computational framework to discover objects and learn their physical properties along this paradigm of Learning from Interaction, and reveals that this agent learns efficiently and effectively; not just for objects it has interacted with before, but also for novel instances from seen categories as well as novel object categories.
...
...