• Publications
  • Influence
Naive Bayes Super-Resolution Forest
TLDR
This paper presents a fast, high-performance method for super resolution with external learning that provides scalability to finer partitions of the underlying coarse patch space. Expand
  • 85
  • 13
  • PDF
Non-Parametric Blur Map Regression for Depth of Field Extension
TLDR
We present a blind deblurring pipeline able to restore spatiallyvarying out-of-focus blurred images by slightly extending their DOF and recovering sharpness in regions slightly out of focus. Expand
  • 24
  • 6
PSyCo: Manifold Span Reduction for Super Resolution
TLDR
The main challenge in Super Resolution (SR) is to discover the mapping between the low-and high-resolution manifolds of image patches, a complex ill-posed problem which has recently been addressed through piecewise linear regression. Expand
  • 33
  • 3
  • PDF
RoboTHOR: An Open Simulation-to-Real Embodied AI Platform
TLDR
We introduce RoboTHOR to democratize research in interactive and embodied visual AI. Expand
  • 13
  • 3
  • PDF
Image-based multi-view scene analysis using 'conexels'
Multi-camera environments allow constructing volumetric models of the scene to improve the analysis performance of computer vision algorithms (e.g. disambiguating occlusion). When representingExpand
  • 16
  • 2
  • PDF
Antipodally Invariant Metrics for Fast Regression-Based Super-Resolution
TLDR
In this paper, we present a very fast regression-based algorithm, which builds on the densely populated anchored neighborhoods and sublinear search structures. Expand
  • 12
  • 2
  • PDF
AllenAct: A Framework for Embodied AI Research
TLDR
We introduce AllenAct, a modular and flexible learning framework designed with a focus on the unique requirements of Embodied AI research. Expand
  • 10
  • 1
  • PDF
Fast Super-Resolution via Dense Local Training and Inverse Regressor Search
TLDR
In this paper we propose a novel inverse-search approach for regression-based Super-Resolution, which improves speed and quality compared to the state-of-the-art. Expand
  • 13
  • 1
  • PDF
Half hypersphere confinement for piecewise linear regression
TLDR
We introduce the Half Hypersphere Confinement (HHC), a fast alternative to Multidimensional Scaling (MDS) that allows to map antipodally invariant distances in the Euclidean space with very little approximation error. Expand
  • 6
  • 1
  • PDF
Robust single-image super-resolution using cross-scale self-similarity
TLDR
We present a noise-aware single-image super-resolution (SI-SR) algorithm, which automatically cancels additive noise while adding detail learned from lower-resolution scales. Expand
  • 5
  • 1
...
1
2
3
4
5
...