Skip to search formSkip to main contentSkip to account menu

RoboTHOR: An Open Simulation-to-Real Embodied AI Platform

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.
View on IEEE (opens in a new tab)

Naive Bayes Super-Resolution Forest

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.
View on IEEE (opens in a new tab)

Non-Parametric Blur Map Regression for Depth of Field Extension

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.
View on IEEE (opens in a new tab)

PSyCo: Manifold Span Reduction for Super Resolution

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.
View on IEEE (opens in a new tab)

AllenAct: A Framework for Embodied AI Research

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.
View PDF on arXiv (opens in a new tab)

Image-based multi-view scene analysis using 'conexels'

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

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.
View on IEEE (opens in a new tab)

Learning About Objects by Learning to Interact with Them

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.
View PDF on arXiv (opens in a new tab)

Fast Super-Resolution via Dense Local Training and Inverse Regressor Search

This paper proposes a novel inverse-search approach for regression-based Super-Resolution by applying spherical hashing to both image and regressors, which reduces the inverse search into computing a trained function.
View via Publisher (opens in a new tab)

Half hypersphere confinement for piecewise linear regression

The usage of antipodally invariant metrics are proposed and introduced and the Half Hypersphere Confinement (HHC), a fast alternative to Multidimensional Scaling (MDS) that allows to map antipodal invariant distances in the Euclidean space with very little approximation error is introduced.
View on IEEE (opens in a new tab)
By clicking accept or continuing to use the site, you agree to the terms outlined in our Privacy Policy (opens in a new tab), Terms of Service (opens in a new tab), and Dataset License (opens in a new tab)