This gallery contains 2 photos.
This paper presents novel methods to handle potential occlusion problems and to render realistically the lighting of embedded virtual 3D objects in photo-based 3D worlds. These 3D worlds are called 3D Photo Collections. The first focus of this work … Continue reading
This gallery contains 1 photo.
In this journal, we present ConGrap, a novel contour detector that uses the Gradient Map and results in closed contours with semantic connections. In contrast to common edge and contour detections, ConGrap not only produces an edge image, but also … Continue reading
This gallery contains 5 photos.
In this paper, we present ConGrap, a novel contour detector that uses the Gradient Map and results in closed contours with semantic connections. In contrast to common edge and contour detections, ConGrap not only produces an edge image, but also … Continue reading
This gallery contains 2 photos.
We present a novel approach for accurate reconstruction of relative radiance of every surface in an augmented image-based 3D scene. By using unordered images with varying exposure of 3D Photo Collections and a 3D mesh of the scene geometry, the … Continue reading
This gallery contains 2 photos.
In this work, we present PoP-EYE, an environment for the fast and efficient development of high quality Mixed Reality (MR) applications using 3D Photo Collections. In addition to photos with geotags, 3D Photo Collections like Google’s Streetview or Microsoft’s Photosynth … Continue reading
This gallery contains 2 photos.
In this paper a novel 3D segmentation of photos is presented. As basis 3D Photo Collections generated by a strcuture-from-motion software are used. A photo will be segmented by given 3D informations to a 3D segment image. Frank Nagl, Paul … Continue reading
This gallery contains 2 photos.
In this paper, we present a method, where handheld snapshots, which are taken from arbitrary viewpoints, can be used to generate a depth map. Starting with a bunch of photos of the same object taken from different viewpoints, the intrinsic and extrinsic … Continue reading
This gallery contains 2 photos.
In this paper, we present a system to handle occlusions of virtual objects through real parts in photos. Based on 3D-Photo-Collections single images are segmented and for all segments a depth position is estimated. Thereby a so-called Sliced-Image is created … Continue reading
This gallery contains 2 photos.
In this paper, we present a novel technique for applying image-based lighting on virtual objects by constructing synthesized environment maps (SEM) automatically. In contrast to related work, we use unordered photo collections as input instead of a completely measured environmental … Continue reading
This gallery contains 2 photos.
In this paper, a generic architecture for image-based 3D applications is presented. The goal is to provide a framework for fast and robust development of 3D applications, which uses photo collections to build photorealistic virtual 3D worlds. Therefore, data-flow-oriented image … Continue reading
This gallery contains 3 photos.
This work presents a novel algorithm to detect correct straight-line segments. In contrast to other works, our algorithm detects straight lines independently of interrupting the line by other segments. This robustness is achieved by a multistage process. First, preprocessing operations … Continue reading
This gallery contains 2 photos.
This work presents the Shader-Based-Image-Processor, a framework for graphics board-based image processing routines of videos in real-time. Thereby, the GPU is used for parallelization of mathematical image processing operations. SBIP is divided in two parts: The core and the set … Continue reading
This gallery contains 3 photos.
In this poster, a system for reconstruction 3D surfaces from a set of photos is presented. Therefore the height for every pixel is estimated by comparing it to all photos and find the photo where it is most focused, resulting … Continue reading
This gallery contains 2 photos.
In this paper, we present a lightweight material and light rendering layer, called MOPS (Minimalistic Operational Preprocessor for Shaders), which simplifies the definition and rendering of light sources as well as material surfaces in real time applications. MOPS generates GLSL … Continue reading
