18 results on '"Alsisan A"'
Search Results
2. Consistent View Synthesis with Pose-Guided Diffusion Models
- Author
-
Tseng, Hung-Yu, Li, Qinbo, Kim, Changil, Alsisan, Suhib, Huang, Jia-Bin, and Kopf, Johannes
- Subjects
Computer Science - Computer Vision and Pattern Recognition - Abstract
Novel view synthesis from a single image has been a cornerstone problem for many Virtual Reality applications that provide immersive experiences. However, most existing techniques can only synthesize novel views within a limited range of camera motion or fail to generate consistent and high-quality novel views under significant camera movement. In this work, we propose a pose-guided diffusion model to generate a consistent long-term video of novel views from a single image. We design an attention layer that uses epipolar lines as constraints to facilitate the association between different viewpoints. Experimental results on synthetic and real-world datasets demonstrate the effectiveness of the proposed diffusion model against state-of-the-art transformer-based and GAN-based approaches., Comment: CVPR 2023. Project page: https://poseguided-diffusion.github.io/
- Published
- 2023
3. A Practical Stereo Depth System for Smart Glasses
- Author
-
Wang, Jialiang, Scharstein, Daniel, Bapat, Akash, Blackburn-Matzen, Kevin, Yu, Matthew, Lehman, Jonathan, Alsisan, Suhib, Wang, Yanghan, Tsai, Sam, Frahm, Jan-Michael, He, Zijian, Vajda, Peter, Cohen, Michael F., and Uyttendaele, Matt
- Subjects
Computer Science - Computer Vision and Pattern Recognition - Abstract
We present the design of a productionized end-to-end stereo depth sensing system that does pre-processing, online stereo rectification, and stereo depth estimation with a fallback to monocular depth estimation when rectification is unreliable. The output of our depth sensing system is then used in a novel view generation pipeline to create 3D computational photography effects using point-of-view images captured by smart glasses. All these steps are executed on-device on the stringent compute budget of a mobile phone, and because we expect the users can use a wide range of smartphones, our design needs to be general and cannot be dependent on a particular hardware or ML accelerator such as a smartphone GPU. Although each of these steps is well studied, a description of a practical system is still lacking. For such a system, all these steps need to work in tandem with one another and fallback gracefully on failures within the system or less than ideal input data. We show how we handle unforeseen changes to calibration, e.g., due to heat, robustly support depth estimation in the wild, and still abide by the memory and latency constraints required for a smooth user experience. We show that our trained models are fast, and run in less than 1s on a six-year-old Samsung Galaxy S8 phone's CPU. Our models generalize well to unseen data and achieve good results on Middlebury and in-the-wild images captured from the smart glasses., Comment: Accepted at CVPR2023
- Published
- 2022
4. LTM: Lightweight Textured Mesh Extraction and Refinement of Large Unbounded Scenes for Efficient Storage and Real-Time Rendering.
- Author
-
Jaehoon Choi, Rajvi Shah, Qinbo Li, Yipeng Wang 0018, Ayush Saraf, Changil Kim 0001, Jia-Bin Huang 0001, Dinesh Manocha, Suhib Alsisan, and Johannes Kopf 0001
- Published
- 2024
- Full Text
- View/download PDF
5. One Shot 3D Photography
- Author
-
Kopf, Johannes, Matzen, Kevin, Alsisan, Suhib, Quigley, Ocean, Ge, Francis, Chong, Yangming, Patterson, Josh, Frahm, Jan-Michael, Wu, Shu, Yu, Matthew, Zhang, Peizhao, He, Zijian, Vajda, Peter, Saraf, Ayush, and Cohen, Michael
- Subjects
Computer Science - Computer Vision and Pattern Recognition ,Computer Science - Graphics - Abstract
3D photography is a new medium that allows viewers to more fully experience a captured moment. In this work, we refer to a 3D photo as one that displays parallax induced by moving the viewpoint (as opposed to a stereo pair with a fixed viewpoint). 3D photos are static in time, like traditional photos, but are displayed with interactive parallax on mobile or desktop screens, as well as on Virtual Reality devices, where viewing it also includes stereo. We present an end-to-end system for creating and viewing 3D photos, and the algorithmic and design choices therein. Our 3D photos are captured in a single shot and processed directly on a mobile device. The method starts by estimating depth from the 2D input image using a new monocular depth estimation network that is optimized for mobile devices. It performs competitively to the state-of-the-art, but has lower latency and peak memory consumption and uses an order of magnitude fewer parameters. The resulting depth is lifted to a layered depth image, and new geometry is synthesized in parallax regions. We synthesize color texture and structures in the parallax regions as well, using an inpainting network, also optimized for mobile devices, on the LDI directly. Finally, we convert the result into a mesh-based representation that can be efficiently transmitted and rendered even on low-end devices and over poor network connections. Altogether, the processing takes just a few seconds on a mobile device, and the result can be instantly viewed and shared. We perform extensive quantitative evaluation to validate our system and compare its new components against the current state-of-the-art., Comment: Project page: https://facebookresearch.github.io/one_shot_3d_photography/ Code: https://github.com/facebookresearch/one_shot_3d_photography
- Published
- 2020
6. Consistent View Synthesis with Pose-Guided Diffusion Models.
- Author
-
Hung-Yu Tseng, Qinbo Li, Changil Kim 0001, Suhib Alsisan, Jia-Bin Huang 0001, and Johannes Kopf 0001
- Published
- 2023
- Full Text
- View/download PDF
7. A Practical Stereo Depth System for Smart Glasses.
- Author
-
Jialiang Wang, Daniel Scharstein, Akash Bapat, Kevin Blackburn-Matzen, Matthew Yu, Jonathan Lehman, Suhib Alsisan, Yanghan Wang, Sam S. Tsai, Jan-Michael Frahm, Zijian He, Peter Vajda, Michael F. Cohen, and Matt Uyttendaele
- Published
- 2023
- Full Text
- View/download PDF
8. Assessment of Sustainable Recycling at the University of Jordan
- Author
-
Moqbel, Shadi, Abu-Zurayk, Rund, Bozeya, Ayat, Alsisan, Ra, and Al Bawab, Abeer
- Abstract
Purpose: This study sought to assess the process of initiating a sustainable recycling program at the University of Jordan. It illustrates the potentials of recycling, perceived awareness of recycling by the students and staff, as well as challenges to a sustainable waste recycling program. This study aims to identify the barriers and challenges that face a sustainable waste recycling program at the University of Jordan. Design/methodology/approach: The study consisted of investigating waste recycling potential on campus, inspecting general environmental awareness toward recycling and running an experimental recycling study on part of the campus. A waste characterization study was conducted to assess the current waste status and recycling extent. A questionnaire survey was carried out to obtain information on the students' and staffs' awareness of waste recycling and management on campus. In the experimental recycling study, seventy units of waste segregation bins were distributed on campus. The recycling efficiency was evaluated at two schools; the School of Engineering and the School of Medicine. The administrative support and collaboration while running the recycling program were also observed. Findings: Overall, waste recycling at the University of Jordan has an appreciable opportunity and potential. A substantial amount of waste can be diverted from going to the landfill. Data showed general positive recycling rates except for plastic. Also, the recycling rates show great potential for enhancing. The recycling at the University of Jordan faces several barriers and obstacles. The greatest barrier was identified as the lack of cooperation of the administrative system on campus. The administrative support for the recycling program was strong only at the initiation of the recycling program. Administrative support has a vital influence on the recycling program. It has the potential of boosting it or bringing it to halt. Future studies should focus on investigating recycling efficiency for the entire campus and focus more on increasing pro-environmental behavior among students and staff in higher education institutions. Originality/value: The value of this research lies in it being conducted in a large campus university in a developing country. Also, the study used a diagnostic approach that is based on evaluating an environmental sustainability program as it evolves inside a higher education institution. The study illustrates the challenges that face universities in developing countries while adopting green campus initiatives.
- Published
- 2020
- Full Text
- View/download PDF
9. A Practical Stereo Depth System for Smart Glasses.
- Author
-
Jialiang Wang, Daniel Scharstein, Akash Bapat, Kevin Blackburn-Matzen, Matthew Yu, Jonathan Lehman, Suhib Alsisan, Yanghan Wang, Sam S. Tsai, Jan-Michael Frahm, Zijian He, Peter Vajda, Michael F. Cohen, and Matt Uyttendaele
- Published
- 2022
- Full Text
- View/download PDF
10. One Shot 3D Photography.
- Author
-
Johannes Kopf 0001, Kevin Matzen, Suhib Alsisan, Ocean Quigley, Francis Ge, Yangming Chong, Josh Patterson, Jan-Michael Frahm, Shu Wu, Matthew Yu, Peizhao Zhang, Zijian He, Peter Vajda, Ayush Saraf, and Michael F. Cohen
- Published
- 2020
11. A Practical Stereo Depth System for Smart Glasses
- Author
-
Wang, Jialiang, primary, Scharstein, Daniel, additional, Bapat, Akash, additional, Blackburn-Matzen, Kevin, additional, Yu, Matthew, additional, Lehman, Jonathan, additional, Alsisan, Suhib, additional, Wang, Yanghan, additional, Tsai, Sam, additional, Frahm, Jan-Michael, additional, He, Zijian, additional, Vajda, Peter, additional, Cohen, Michael F., additional, and Uyttendaele, Matt, additional
- Published
- 2023
- Full Text
- View/download PDF
12. Consistent View Synthesis with Pose-Guided Diffusion Models
- Author
-
Tseng, Hung-Yu, primary, Li, Qinbo, additional, Kim, Changil, additional, Alsisan, Suhib, additional, Huang, Jia-Bin, additional, and Kopf, Johannes, additional
- Published
- 2023
- Full Text
- View/download PDF
13. Casual 3D photography.
- Author
-
Peter Hedman, Suhib Alsisan, Richard Szeliski, and Johannes Kopf 0001
- Published
- 2017
- Full Text
- View/download PDF
14. Variation-Factored Encoding of Facade Images.
- Author
-
Suhib Alsisan and Niloy J. Mitra
- Published
- 2012
- Full Text
- View/download PDF
15. Assessment of sustainable recycling at The University of Jordan
- Author
-
Rund Abu-Zurayk, Abeer Al Bawab, Raed Alsisan, Ayat Bozeya, and Shadi Moqbel
- Subjects
Sustainable development ,Municipal solid waste ,Sanitation ,Higher education ,Process (engineering) ,business.industry ,020209 energy ,Developing country ,Questionnaire ,Human Factors and Ergonomics ,02 engineering and technology ,010501 environmental sciences ,01 natural sciences ,Education ,Sustainability ,0202 electrical engineering, electronic engineering, information engineering ,Business ,Environmental planning ,0105 earth and related environmental sciences - Abstract
Purpose This study sought to assess the process of initiating a sustainable recycling program at the University of Jordan. It illustrates the potentials of recycling, perceived awareness of recycling by the students and staff, as well as challenges to a sustainable waste recycling program. This study aims to identify the barriers and challenges that face a sustainable waste recycling program at the University of Jordan. Design/methodology/approach The study consisted of investigating waste recycling potential on campus, inspecting general environmental awareness toward recycling and running an experimental recycling study on part of the campus. A waste characterization study was conducted to assess the current waste status and recycling extent. A questionnaire survey was carried out to obtain information on the students’ and staffs’ awareness of waste recycling and management on campus. In the experimental recycling study, seventy units of waste segregation bins were distributed on campus. The recycling efficiency was evaluated at two schools; the School of Engineering and the School of Medicine. The administrative support and collaboration while running the recycling program were also observed. Findings Overall, waste recycling at the University of Jordan has an appreciable opportunity and potential. A substantial amount of waste can be diverted from going to the landfill. Data showed general positive recycling rates except for plastic. Also, the recycling rates show great potential for enhancing. The recycling at the University of Jordan faces several barriers and obstacles. The greatest barrier was identified as the lack of cooperation of the administrative system on campus. The administrative support for the recycling program was strong only at the initiation of the recycling program. Administrative support has a vital influence on the recycling program. It has the potential of boosting it or bringing it to halt. Future studies should focus on investigating recycling efficiency for the entire campus and focus more on increasing pro-environmental behavior among students and staff in higher education institutions. Originality/value The value of this research lies in it being conducted in a large campus university in a developing country. Also, the study used a diagnostic approach that is based on evaluating an environmental sustainability program as it evolves inside a higher education institution. The study illustrates the challenges that face universities in developing countries while adopting green campus initiatives.
- Published
- 2020
- Full Text
- View/download PDF
16. One shot 3D photography
- Author
-
Kopf, Johannes, primary, Matzen, Kevin, additional, Alsisan, Suhib, additional, Quigley, Ocean, additional, Ge, Francis, additional, Chong, Yangming, additional, Patterson, Josh, additional, Frahm, Jan-Michael, additional, Wu, Shu, additional, Yu, Matthew, additional, Zhang, Peizhao, additional, He, Zijian, additional, Vajda, Peter, additional, Saraf, Ayush, additional, and Cohen, Michael, additional
- Published
- 2020
- Full Text
- View/download PDF
17. One Shot 3D Photography
- Author
-
Michael F. Cohen, Suhib Alsisan, Jan-Michael Frahm, Zijian He, Kevin Matzen, Ocean Quigley, Josh Patterson, Yangming Chong, Shu Wu, Johannes Kopf, Ayush Saraf, Peizhao Zhang, Francis Ge, Peter Vajda, and Matthew Chuck-Jun Yu
- Subjects
FOS: Computer and information sciences ,Monocular ,Computer science ,business.industry ,Computer Vision and Pattern Recognition (cs.CV) ,Computer Science - Computer Vision and Pattern Recognition ,Latency (audio) ,Inpainting ,ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION ,020207 software engineering ,02 engineering and technology ,Virtual reality ,Computer Graphics and Computer-Aided Design ,Graphics (cs.GR) ,Moment (mathematics) ,Computer Science - Graphics ,0202 electrical engineering, electronic engineering, information engineering ,Computer vision ,Artificial intelligence ,Representation (mathematics) ,business ,Parallax - Abstract
3D photography is a new medium that allows viewers to more fully experience a captured moment. In this work, we refer to a 3D photo as one that displays parallax induced by moving the viewpoint (as opposed to a stereo pair with a fixed viewpoint). 3D photos are static in time, like traditional photos, but are displayed with interactive parallax on mobile or desktop screens, as well as on Virtual Reality devices, where viewing it also includes stereo. We present an end-to-end system for creating and viewing 3D photos, and the algorithmic and design choices therein. Our 3D photos are captured in a single shot and processed directly on a mobile device. The method starts by estimating depth from the 2D input image using a new monocular depth estimation network that is optimized for mobile devices. It performs competitively to the state-of-the-art, but has lower latency and peak memory consumption and uses an order of magnitude fewer parameters. The resulting depth is lifted to a layered depth image, and new geometry is synthesized in parallax regions. We synthesize color texture and structures in the parallax regions as well, using an inpainting network, also optimized for mobile devices, on the LDI directly. Finally, we convert the result into a mesh-based representation that can be efficiently transmitted and rendered even on low-end devices and over poor network connections. Altogether, the processing takes just a few seconds on a mobile device, and the result can be instantly viewed and shared. We perform extensive quantitative evaluation to validate our system and compare its new components against the current state-of-the-art., Comment: Project page: https://facebookresearch.github.io/one_shot_3d_photography/ Code: https://github.com/facebookresearch/one_shot_3d_photography
- Published
- 2020
- Full Text
- View/download PDF
18. Casual 3D photography
- Author
-
Hedman, Peter, primary, Alsisan, Suhib, additional, Szeliski, Richard, additional, and Kopf, Johannes, additional
- Published
- 2017
- Full Text
- View/download PDF
Catalog
Discovery Service for Jio Institute Digital Library
For full access to our library's resources, please sign in.