Zobrazeno 1 - 10
of 55
pro vyhledávání: '"Gallo, Orazio"'
Wide field-of-view (FoV) cameras efficiently capture large portions of the scene, which makes them attractive in multiple domains, such as automotive and robotics. For such applications, estimating depth from multiple images is a critical task, and t
Externí odkaz:
http://arxiv.org/abs/2401.13786
Autor:
Wang, Jiashun, Li, Xueting, Liu, Sifei, De Mello, Shalini, Gallo, Orazio, Wang, Xiaolong, Kautz, Jan
Transferring the pose of a reference avatar to stylized 3D characters of various shapes is a fundamental task in computer graphics. Existing methods either require the stylized characters to be rigged, or they use the stylized character in the desire
Externí odkaz:
http://arxiv.org/abs/2306.00200
Modern avatar generators allow anyone to synthesize photorealistic real-time talking avatars, ushering in a new era of avatar-based human communication, such as with immersive AR/VR interactions or videoconferencing with limited bandwidths. Their saf
Externí odkaz:
http://arxiv.org/abs/2305.03713
Rendering articulated objects while controlling their poses is critical to applications such as virtual reality or animation for movies. Manipulating the pose of an object, however, requires the understanding of its underlying structure, that is, its
Externí odkaz:
http://arxiv.org/abs/2112.11347
Autor:
Chan, Eric R., Lin, Connor Z., Chan, Matthew A., Nagano, Koki, Pan, Boxiao, De Mello, Shalini, Gallo, Orazio, Guibas, Leonidas, Tremblay, Jonathan, Khamis, Sameh, Karras, Tero, Wetzstein, Gordon
Unsupervised generation of high-quality multi-view-consistent images and 3D shapes using only collections of single-view 2D photographs has been a long-standing challenge. Existing 3D GANs are either compute-intensive or make approximations that are
Externí odkaz:
http://arxiv.org/abs/2112.07945
Recent approaches to render photorealistic views from a limited set of photographs have pushed the boundaries of our interactions with pictures of static scenes. The ability to recreate moments, that is, time-varying sequences, is perhaps an even mor
Externí odkaz:
http://arxiv.org/abs/2105.05994
Publikováno v:
British Machine Vision Conference (BMVC) 2021
We tackle the problem of predicting saliency maps for videos of dynamic scenes. We note that the accuracy of the maps reconstructed from the gaze data of a fixed number of observers varies with the frame, as it depends on the content of the scene. Th
Externí odkaz:
http://arxiv.org/abs/2104.08038
Time-to-contact (TTC), the time for an object to collide with the observer's plane, is a powerful tool for path planning: it is potentially more informative than the depth, velocity, and acceleration of objects in the scene -- even for humans. TTC pr
Externí odkaz:
http://arxiv.org/abs/2101.04777
Content creation, central to applications such as virtual reality, can be a tedious and time-consuming. Recent image synthesis methods simplify this task by offering tools to generate new views from as little as a single input image, or by converting
Externí odkaz:
http://arxiv.org/abs/2008.09106
Stereo-based depth estimation is a cornerstone of computer vision, with state-of-the-art methods delivering accurate results in real time. For several applications such as autonomous navigation, however, it may be useful to trade accuracy for lower l
Externí odkaz:
http://arxiv.org/abs/2005.07274