Underwater depth prediction plays an important role in underwater vision research. Because of the complex environment, it is extremely difficult and expensive to obtain datasets with reliable annotation. Thus, map estimation a data-driven manner still challenging task. To tackle this problem, we propose end-to-end system including two different modules for image synthesis estimation, respective...

Coplanarity is a relationship of a set of points that exist on a single plane. Coplanarities can be easily observed in a scene with planer surfaces, and these types of coplanarities have been widely used for 3D reconstructions based on geometrical constraints. Other types of coplanarities that can be observed from images are those observed as cross sections of planes and scenes; for example, po...

This paper proposes an efficient technique for human motion recognition based on motion history images and an eigenspace technique. In recent years, human motion recognition has become one of the most popular research fields. It is expected to be applied in a security system, man-machine communication, and so on. In the proposed technique, we use two feature images and the eigenspace technique ...

In this paper, we propose a quality metric for three-dimensional images or videos. The goal of this work is to provide a quality measurement from the relationship between the depth image quality and the three-dimensional perception. From our observation, we found that there is a relation between the perception of depth and the formation of object. The consistency for depth and object perception...

Software-based, the focal depth in light microscopic photographic images can be enhanced fundamentally. Thus, three dimensional images are achievable, comparable with scanning electron microscopic results. Moreover several parameters which determine the quality of microscopic images can be improved by averaging. For these purposes, a vertical stack has to be taken as sequence or scan, consistin...

This paper presents a novel approach to depth recovery from image blur by zooming. We first discuss the optical properties of a zoom lens system; the image blur varies according to zoom as well as focus and iris settings. Then a thin lens based camera model is proposed that is characterized by the effective focal length and lens diameter. Using this model, we have proved that the depth informat...

Differently from traditional two-dimensional texture images, the depth images of three-dimensional (3D) video systems have significant sparse characteristics under the certain transform basis, which make it possible for compressive sensing to represent depth information efficiently. Therefore, in this paper, a novel depth image coding scheme is proposed based on a block compressive sensing meth...

In this project, we propose a novel approach for estimating depth from RGB images. Traditionally, most work uses a single RGB image to estimate depth, which is inherently difficult and generally results in poor performance – even with thousands of data examples. In this work, we alternatively use multiple RGB images that were captured while changing the focus of the camera’s lens. This method l...

This paper describes a method of extracting depth information about a scene from a single, static viewpoint. The. approach uses aperture variation to obtain a sequence of images differing only in depth of field, thus avoiding the 'correspondence problem associated with stereo and optical flow techniques. These images contain the necessary coded depth information. By using one image (that with t...

A depth image provides partial geometric information of a 3D scene, namely the shapes of physical objects as observed from a particular viewpoint. This information is important when synthesizing images of different virtual camera viewpoints via depth-image-based rendering (DIBR). It has been shown that depth images can be efficiently coded using contour-adaptive codecs that preserve edge sharpn...