We frame the problem of local representation of imaging data as the computation of minimal sufficient statistics that are invariant to nuisance variability induced by viewpoint and illumination. We show that, under very stringent condi-tions, these are related to “feature descriptors ” commonly used in Computer Vision. Such conditions can be relaxed if multiple views of the same scene are available. We pro-pose a sampling-based and a point-estimate based approx-imation of such a representation, compared empirically on image-to-(multiple)image matching, for which we introduce a multi-view wide-baseline matching benchmark, consisting of a mixture of real and synthetic objects with ground truth camera motion and dense three-dimensional geometr...
Object recognition from a single view fails when the available features are not sufficient to determ...
The problem of determining feature correspondences across multiple views is considered. The term &qu...
In this paper, we investigate detection and localization of general 3D object classes by relating lo...
We propose an extension of popular descriptors based on gradient orientation histograms (HOG, comput...
We present a robust feature matching approach that considers features from more than two images duri...
This paper presents a multiview model of object categories, generally applicable to virtually any ty...
Estimating the optimal representation from sensor data has been one of the most challenging problems...
Sensors record our physical world through their 2D projection, e.g., in the form of RGB or RGB-D ima...
Local image features are generally robust to different geometric and photometric transformations on ...
In this paper we present a novel approach for generating viewpoint invariant features from single im...
Abstract. While the majority of computer vision systems are based on representing images by local fe...
Abstract. In this paper we introduce a robust matching technique that allows to operate a very accur...
We present a multi-view stereo algorithm that addresses the extreme changes in lighting, scale, clut...
In this paper we introduce a robust matching technique that allows to operate a very accurate select...
We present a multi-view stereo algorithm that addresses the extreme changes in lighting, scale, clut...
Object recognition from a single view fails when the available features are not sufficient to determ...
The problem of determining feature correspondences across multiple views is considered. The term &qu...
In this paper, we investigate detection and localization of general 3D object classes by relating lo...
We propose an extension of popular descriptors based on gradient orientation histograms (HOG, comput...
We present a robust feature matching approach that considers features from more than two images duri...
This paper presents a multiview model of object categories, generally applicable to virtually any ty...
Estimating the optimal representation from sensor data has been one of the most challenging problems...
Sensors record our physical world through their 2D projection, e.g., in the form of RGB or RGB-D ima...
Local image features are generally robust to different geometric and photometric transformations on ...
In this paper we present a novel approach for generating viewpoint invariant features from single im...
Abstract. While the majority of computer vision systems are based on representing images by local fe...
Abstract. In this paper we introduce a robust matching technique that allows to operate a very accur...
We present a multi-view stereo algorithm that addresses the extreme changes in lighting, scale, clut...
In this paper we introduce a robust matching technique that allows to operate a very accurate select...
We present a multi-view stereo algorithm that addresses the extreme changes in lighting, scale, clut...
Object recognition from a single view fails when the available features are not sufficient to determ...
The problem of determining feature correspondences across multiple views is considered. The term &qu...
In this paper, we investigate detection and localization of general 3D object classes by relating lo...