Despite of exciting advances in image-based rendering and novel view synthesis, it is still challenging to achieve high-resolution results that can reach production-level quality when applying such methods to the task...
Despite of exciting advances in image-based rendering and novel view synthesis, it is still challenging to achieve high-resolution results that can reach production-level quality when applying such methods to the task of stereo conversion. At the same time, only very few dedicated stereo conversion approaches exist, which also fall short in terms of the required quality. Hence, in this paper, we present a novel method for high-resolution 2D-to-3D conversion. It is fully differentiable in all of its stages and performs disparity-informed warping, consistent foreground-background compositing, and background-aware inpainting. To enable temporal consistency in the resulting video, we propose a strategy to integrate information from additional video frames. Extensive ablation studies validate our design choices, leading to a fully automatic model that outperforms existing approaches by a large margin (49-70% LPIPS error reduction). Finally, inspired from current practices in manual stereo conversion, we introduce optional interactive tools into our model, which allow to steer the conversion process and make it significantly more applicable for 3D film production.
3D displays are coming phenomenon of the nearest future and it is expected that 3D displays will be widely available soon. There are currently some 3D displays available and also some notebooks with 3D display as Shar...
详细信息
3D displays are coming phenomenon of the nearest future and it is expected that 3D displays will be widely available soon. There are currently some 3D displays available and also some notebooks with 3D display as Sharp AL3D. The viewing position is quite restricted spatially in the case of 3D displays and also the (visual information for the left eye is taken by the right eye and vice versa) causes some severe problems in 3D image perception. This paper addresses several issues concerning 3D perception based on stereo-images. Another issues related to 3D stereo video perception, like discontinuities between frames etc. are not described here.
The compensation for brain shift is assisted by intraoperative imaging. For the purpose of fast registration and interactive visualization, a framework is presented based on local desktop computers and remote high-end...
详细信息
Haptic applications are difficult to debug due to their high update rate and many factors influencing their execution. In this paper, we describe a practical visual debugger for single-point-of-contact haptic devices ...
详细信息
This (video-) paper describes a user interface concept, which facilitates multidimensional visual queries, filtering and browsing of the file system at the same time by means of the "liquid scatter space" (L...
详细信息
This (video-) paper describes a user interface concept, which facilitates multidimensional visual queries, filtering and browsing of the file system at the same time by means of the "liquid scatter space" (LSS) concept (Waldeck, 2004). The UI concept is based on an advanced star field display (Ahlberg & Shneiderman, 1994) using liquid browsing (Waldeck, 2004) and selection based (sketch-) queries. It allows realtime search and browsing at the same time (integrated into one single user interface) and can visualize the most important file system meta data dimensions simultaneously: 1. filename; 2. creation/modification date; 3. filesize; 4. filetype; and 5. label. LSS provides very fast and easy visual data mining possibilities for the desktop and makes it possible to perceive complex dependencies between the most important file system meta data properties at a glance. It also overcomes the "hidden-deep-down-in-hierarchy-structures"-problem by making it possible to use folders for structuring but not being bound to them. This paper focuses on visual design and interaction aspects and emphasizes the importance of paying regard to visual interactive details for information visualization and interaction interfaces and the need of making it easy to use.
This paper focuses on digitally-supported research methods for an important group of cultural heritage objects, the Greek pottery, especially with figured decoration. The design, development and application of new dig...
详细信息
This paper presents a method to automatically calculate texture maps for a given 3D object from a sequence of images. It is used in our image-based modeling approach after the registration of the images and the geomet...
详细信息
This paper presents a method to automatically calculate texture maps for a given 3D object from a sequence of images. It is used in our image-based modeling approach after the registration of the images and the geometric modeling has been done. We show that the presented method uses the information from all images by implicitly applying a weighting function. Using this approach, the consideration of modeled occlusions as well as the detection and removal of non-modeled occlusions is accomplished. The final resolution of the texture maps can be adjusted on a pixel/cm basis.
Magnetocardiograph (MCG) is one of the most useful diagnosing tools for myocardial ischemic diseases and the conduction abnormality, since the technique directly measures magnetic fields generated by myocardial curren...
详细信息
暂无评论