Publicaties
Gekozen filters:
Gekozen filters:
Segmentation-based intra coding of depth maps using texture information Vrije Universiteit Brussel
Emerging video technologies, such as 3DTV, increase the demand for high efficiency coding tools. To allow the transmission of a multiview video over the employed transmission channels, a new data format including texture and the corresponding depth information has been proposed. In this paper we present a novel segmentation-based intra codec for depth maps, utilizing the correlation between depth and color data. Our system performs a ...
High-Quality View Interpolation Based on Depth Maps and Its Hardware Implementation Universiteit Hasselt
Three dimensional (3D) vision applications have drawn more attention nowadays and many products are entering the mass market. View interpolation is a crucial step to generate intermediate viewpoints from reference images. However, it is still challenging to achieve good performance in both processing speed and image quality for various 3D applications. In this paper, a hardware-compatible view interpolation algorithm is proposed, which can ...
Improving depth maps with limited user input KU Leuven
A vastly growing number of productions from the entertainment industry are aiming at 3D movie theaters. These productions use a two-view format, primarily intended for eye-wear assisted viewing in a well defined environment. To get this 3D content into the home environment, where a large variety of 3D viewing conditions exists (e.g. different display sizes, display types, viewing distances), we need a flexible 3D format that can adjust the depth ...
Stroke-based Creation of Depth Maps Universiteit Hasselt
Depth information opens up a lot of possibilities for meaningful editing of photographs. So far, it has only been possible to acquire depth information by either using additional hardware, restrictive scene assumptions or extensive manual input. We developed a novel user-assisted technique for creating adequate depth maps with an intuitive stroke-based user interface. Starting from absolute depth constraints as well as surface normal ...
Multiview and depth map compression based on HEVC Universiteit Gent
In this paper, we show that even with very efficient single-view coding tools like used in High Efficiency Video Coding (HEVC), additional gains from multiview compression can still be obtained. For the texture information, the total bitrate can be reduced by 37.2% on average, compared to simulcast. For depth map information, additional gains largely depend on the quality of the content.
Depth map inpainting and super-resolution with arbitrary scale factors Universiteit Gent
Stixels estimation without depth map computation KU Leuven
Mobile robots require object detection and classification for safe and smooth navigation. Stereo vision improves such detection by doubling the views of the scene and by giving indirect access to depth information. This depth information can also be used to reduce the set of candidate detection windows. Up to now, most algorithms compute a depth map to discard unpromising detection windows. We propose a novel approach where a stixel world model ...
Superpixel-based depth map estimation using defocus blur Vrije Universiteit Brussel
Depth from defocus (DFD) technique calculates the blur amount in images considering that the depth and defocus blur are related to each other. Existing blur estimation methods generally compute the blur at edge locations and solve an optimization problem to propagate the blur from edges to all image pixels. Solving the pixel-based optimization problem is time-consuming and it is the performance bottleneck of current approaches. Moreover, the ...
Joint complexity and rate optimization for 3DTV depth map encoding Universiteit Gent
Current research towards 3D video compression within MPEG requires the compression of three texture and depth views. To reduce the additional complexity and bit rate of the depth map encoding, we present a fast mode decision model based on previously encoded macroblocks of the texture view. Meanwhile we present techniques to reduce the rate based on predicting syntax elements from the corresponding texture view. The proposed system is able to ...