Single Image Depth Estimation With Integration of Parametric Learning and Non-Parametric Sampling

Depth Extraction from Video Using Non-parametric Sampling

We describe a technique that automatically generates plausible depth maps from videos using non-parametric depth sampling. We demonstrate our technique in cases where past methods fail (nontranslating cameras and dynamic scenes). Our technique is applicable to single images as well as videos. For videos, we use local motion cues to improve the inferred depth maps, while optical flow is used to ...

Non-parametric Depth Estimation for Images from a Single Reference Depth

We present a non-parametric method for estimating depth of a single still image. We start from a single reference image and its corresponding 3-d depth and use an unsupervised neural network to transform the reference depth to represent the target image. In doing so, we attempt to mimic the human vision capability of perceiving the depth of a given image. Existing depth recovery methods either ...

Optimal learning for sequential sampling with non-parametric beliefs

We propose a sequential learning policy for ranking and selection problems, where we use a non-parametric procedure for estimating the value of a policy. Our estimation approach aggregates over a set of kernel functions in order to achieve a more consistent estimator. Each element in the kernel estimation set uses a di erent bandwidth to achieve better aggregation. The nal estimate uses a weigh...

Learning Graph Structure With Parametric and Non-Parametric Models

In discrete undirected graphical models, the conditional independence of the node labels Y is specified by the graph structure. We study the case where there is another input random vector X (e.g. observed features) such that the distribution P (Y | X) is determined by functions of X that characterize the (higher-order) interactions among the Y ’s. The main contribution is to learn the graph st...

Non–parametric volatility estimation