Zobrazeno 1 - 10
of 181
pro vyhledávání: '"Izadi, Shahram"'
Autor:
Rebain, Daniel, Angles, Baptiste, Valentin, Julien, Vining, Nicholas, Peethambaran, Jiju, Izadi, Shahram, Tagliasacchi, Andrea
Publikováno v:
Computer Graphics Forum 38 (2019) 5-18
The medial axis transform has applications in numerous fields including visualization, computer graphics, and computer vision. Unfortunately, traditional medial axis transformations are usually brittle in the presence of outliers, perturbations and/o
Externí odkaz:
http://arxiv.org/abs/2010.05066
Autor:
Tang, Danhang, Singh, Saurabh, Chou, Philip A., Haene, Christian, Dou, Mingsong, Fanello, Sean, Taylor, Jonathan, Davidson, Philip, Guleryuz, Onur G., Zhang, Yinda, Izadi, Shahram, Tagliasacchi, Andrea, Bouaziz, Sofien, Keskin, Cem
We describe a novel approach for compressing truncated signed distance fields (TSDF) stored in 3D voxel grids, and their corresponding textures. To compress the TSDF, our method relies on a block-based neural network architecture trained end-to-end,
Externí odkaz:
http://arxiv.org/abs/2005.08877
Autor:
Isack, Hossam, Haene, Christian, Keskin, Cem, Bouaziz, Sofien, Boykov, Yuri, Izadi, Shahram, Khamis, Sameh
We propose a novel efficient and lightweight model for human pose estimation from a single image. Our model is designed to achieve competitive results at a fraction of the number of parameters and computational cost of various state-of-the-art method
Externí odkaz:
http://arxiv.org/abs/2002.03933
Autor:
Angles, Baptiste, Rebain, Daniel, Macklin, Miles, Wyvill, Brian, Barthe, Loic, Lewis, JP, von der Pahlen, Javier, Izadi, Shahram, Valentin, Julien, Bouaziz, Sofien, Tagliasacchi, Andrea
We extend the formulation of position-based rods to include elastic volumetric deformations. We achieve this by introducing an additional degree of freedom per vertex -- isotropic scale (and its velocity). Including scale enriches the space of possib
Externí odkaz:
http://arxiv.org/abs/1906.05260
Autor:
Pandey, Rohit, Tkach, Anastasia, Yang, Shuoran, Pidlypenskyi, Pavel, Taylor, Jonathan, Martin-Brualla, Ricardo, Tagliasacchi, Andrea, Papandreou, George, Davidson, Philip, Keskin, Cem, Izadi, Shahram, Fanello, Sean
Volumetric (4D) performance capture is fundamental for AR/VR content generation. Whereas previous work in 4D performance capture has shown impressive results in studio settings, the technology is still far from being accessible to a typical consumer
Externí odkaz:
http://arxiv.org/abs/1905.12162
Autor:
Martin-Brualla, Ricardo, Pandey, Rohit, Yang, Shuoran, Pidlypenskyi, Pavel, Taylor, Jonathan, Valentin, Julien, Khamis, Sameh, Davidson, Philip, Tkach, Anastasia, Lincoln, Peter, Kowdle, Adarsh, Rhemann, Christoph, Goldman, Dan B, Keskin, Cem, Seitz, Steve, Izadi, Shahram, Fanello, Sean
Motivated by augmented and virtual reality applications such as telepresence, there has been a recent focus in real-time performance capture of humans under motion. However, given the real-time constraint, these systems often suffer from artifacts in
Externí odkaz:
http://arxiv.org/abs/1811.05029
Autor:
Keskin, Cem, Izadi, Shahram
We present SplineNets, a practical and novel approach for using conditioning in convolutional neural networks (CNNs). SplineNets are continuous generalizations of neural decision graphs, and they can dramatically reduce runtime complexity and computa
Externí odkaz:
http://arxiv.org/abs/1810.13118
Autor:
Khamis, Sameh, Fanello, Sean, Rhemann, Christoph, Kowdle, Adarsh, Valentin, Julien, Izadi, Shahram
This paper presents StereoNet, the first end-to-end deep architecture for real-time stereo matching that runs at 60 fps on an NVidia Titan X, producing high-quality, edge-preserved, quantization-free disparity maps. A key insight of this paper is tha
Externí odkaz:
http://arxiv.org/abs/1807.08865
Autor:
Zhang, Yinda, Khamis, Sameh, Rhemann, Christoph, Valentin, Julien, Kowdle, Adarsh, Tankovich, Vladimir, Schoenberg, Michael, Izadi, Shahram, Funkhouser, Thomas, Fanello, Sean
In this paper we present ActiveStereoNet, the first deep learning solution for active stereo systems. Due to the lack of ground truth, our method is fully self-supervised, yet it produces precise depth with a subpixel precision of $1/30th$ of a pixel
Externí odkaz:
http://arxiv.org/abs/1807.06009
Real-time, high-quality, 3D scanning of large-scale scenes is key to mixed reality and robotic applications. However, scalability brings challenges of drift in pose estimation, introducing significant errors in the accumulated model. Approaches often
Externí odkaz:
http://arxiv.org/abs/1604.01093