This paper presents a novel and fully automatic technique to estimate depth information from a single input image. The proposed method is based on a new image classification technique able to classify digital images (also in Bayer pattern format) as indoor, outdoor with geometric elements or outdoor without geometric elements. Using the information collected in the classification step a suitabl...

This paper describes the implementation of a stereo depth measurement algorithm in hardware on Field-Programmable Gate Arrays (FPGAs). This system generates 5-bit pixel disparities on 512 by 480 pixel images at video rate (30 frames/sec). The algorithm implemented is a window based scan-line correlation search technique. Hardware implementation speeds up the performance more than 100 times that...

Most of existing image retargeting approaches only use color information to help preserve important image content. In this paper, we exploit both color and depth information captured by an RGB-D camera to preserve important regions and maintain background structure. In particular, we introduce a depth-based importance map, such that deformation of the image is guided by this map. This depth-bas...

The video-plus-depth data representation uses a regular texture video enriched with the so-called depth map, providing the depth distance for each pixel. The compression efficiency is usually higher for smooth, gray level data representing the depth map than for classical video texture. However, improvements of the coding efficiency are still possible, taking into account the fact that the vide...

Depth boundaries often lose sharpness when upsampling from low-resolution (LR) depth maps especially at large upscaling factors. We present a new method to address the problem of depth map super resolution in which a high-resolution (HR) depth map is inferred from a LR depth map and an additional HR intensity image of the same scene. We propose a Multi-Scale Guided convolutional network (MSG-Ne...

3D technology increases the visual quality as compared to 2D technology.DIBR (Depth Image Based Rendering) technique is used to convert 2D to 3D using a single color image and it’s corresponding depth map. But the main problem with DIBR is that the generated 3D quality is of low quality due to the presence of disocclusions in the depth map. This work proposes an adaptive multimode filtering of ...

This paper describes a new method to automatically generate digital bas-reliefs with depth-of-field effects from general scenes. Most previous methods for bas-relief generation take input in the form of 3D models. However, obtaining 3D models of real scenes or objects is often difficult, inaccurate, and time-consuming. From this motivation, we developed a method that takes as input a set of pho...

A depth image-based rendering (DIBR) technique is one of the rendering processes of virtual views with a color image and the corresponding depth map. The most important issue of DIBR is that the virtual view has no information at newly exposed areas, so called disocclusion. The general solution is to smooth the depth map using a Gaussian smoothing filter before 3D warping. However, the filtered...