We consider the problem of dense depth prediction from a sparse set of depth measurements and a single RGB image. Since depth estimation from monocular images alone is inherently ambiguous and unreliable, to attain a higher level of robustness and accuracy, we introduce additional sparse depth samples, which are either acquired with a low-resolution depth sensor or computed via visual Simultane...

In three-dimensional (3-D) cluttered scenes such as foliage, deeper surfaces often are more shadowed and hence darker, and so depth and luminance often have negative covariance. We examined whether the sign of depth-luminance covariance plays a role in depth perception in 3-D clutter. We compared scenes rendered with negative and positive depth-luminance covariance where positive covariance mea...

This paper presents an e cient technique for unsupervised content-based segmentation in stereoscopic video sequences by appropriately combined di erent content descriptors in a hierarchical framework. Three main modules are involved in the proposed scheme; extraction of reliable depth information, image partition into color and depth regions and a constrained fusion algorithm of color segments ...

A data depth is one of the most important concepts of nonparametric multivariate analysis. Several depth functions have been introduced since 1980. The halfspace depth is probably the most popular. This depth function has many desirable properties (they are stated in the general definition of statictical depth function). We show a way of generalization of the halfspace depth finding a broader c...

This paper studies single-image depth perception in the wild, i.e., recovering depth from a single image taken in unconstrained settings. We introduce a new dataset “Depth in the Wild” consisting of images in the wild annotated with relative depth between pairs of random points. We also propose a new algorithm that learns to estimate metric depth using annotations of relative depth. Compared to...

We present a framework for localizing and opening doors that fall within our current field of view, using Playbot, a computer controlled wheelchair that is equipped with vision sensors and a 6+2 degrees of freedom robotic arm. Contributions of the paper include: (i) Reliable detection of a specular door handle from close distances, where intense specularities tend to make many object detection ...

This paper describes a PDE-based method for dense depth extraction from multiple wide-baseline images. Emphasis lies on the usage of only a small amount of images. The integration of these multiple wide-baseline views is guided by the relative confidence that the system has in the matching to different views. This weighting is fine-grained in that it is determined for every pixel at every itera...

Participatory sensing is a powerful paradigm that leverages information sent by smartphone users to collect fine-grained information on events of interest. Given participatory sensing applications rely completely on the users’ willingness to submit up-to-date and reliable information, it is paramount to effectively incentivize users’ active and reliable participation. In this paper, we survey e...