A new system combines video of a scene from multiple cameras to created 4D visualizations. This makes it possible to view the scene from a variety of angles, place people into new scenes or, in this case, remove someone from a scene.
Carnegie Mellon Approach Requires Neither Studio nor Specialized Cameras
Researchers at Carnegie Mellon University have demonstrated that they can combine iPhone videos shot “in the wild” by separate cameras to create 4D visualizations that allow viewers to watch action from various angles, or even erase people or objects that temporarily block sight lines.
Imagine a visualization of a wedding reception, where dancers can be seen from as many angles as there were cameras, and the tipsy guest who walked in front of the bridal party is nowhere to be seen.
The videos can be shot independently from variety of vantage points, as might occur at a wedding or birthday celebration, said Aayush Bansal, a Ph.D. student in CMU’s Robotics Institute. It also is possible to record actors in one setting and then insert them into another, he added.
Bansal and his colleagues worked around that limitation by using convolutional neural nets (CNNs), a type of deep learning program that has proven adept at analyzing visual data. They found that scene-specific CNNs could be used to compose different parts of the scene.
The CMU researchers demonstrated their method using up to 15 iPhones to capture a variety of scenes — dances, martial arts demonstrations and even flamingos at the National Aviary in Pittsburgh.
The Latest Updates from Bing News & Google News
Go deeper with Bing News on:
- Secretlab Game of Thrones Iron Anniversary Edition Chair Review: A Throne Fit for a Kingon June 9, 2021 at 2:17 pm
The name Secretlab is synonymous with gaming. They make some of the best -- if not the best -- gaming chairs. If you're in the market for something to keep you comfortable during long sessions of open ...
- 'it's a form of art, but there's so much science behind what we do' – slashcube's thomas vournazos on architectural visualizationon June 9, 2021 at 10:26 am
(DB): can you tell us a little about your background and how you became involved in the world of architectural visualization? thomas vournazos (TV): well I am basically an architect, graduated with a ...
- Global Grow Medium Market Size, Opportunities, Growth Rate, Development Trend and Feasibility Studies 2021 to 2027on June 2, 2021 at 2:57 am
Jun 02, 2021 (The Expresswire) -- "Final Report will add the analysis of the impact of COVID-19 on this industry" “Grow Medium Market” report 2021 ...
- Bruker Launches TimsTOF TrueSCP for Unbiased Single Cell 4D-Proteomics and Next-gen TimsTOF Pro 2 with Unprecedented Proteomic Depthon June 1, 2021 at 8:41 am
New PaSER real-time 4D-Proteomics software enables visualization of MOMA CCS-enabled separation of co-eluting or isobaric peptides, advances phosphoproteomics cancer research; GPUde novo peptide ...
- Bruker Launches timsTOF trueSCP for Unbiased Single Cell 4D-Proteomics and Next-gen timsTOF Pro 2 with Unprecedented Proteomic Depthon June 1, 2021 at 4:00 am
Bruker Corporation (Nasdaq: BRKR) today announced the launch of two new timsTOF instruments. They further advance and enable new applications and methods in unbiased proteomics, epiproteomics/PTM ...
Go deeper with Google Headlines on:
Go deeper with Bing News on:
Convolutional neural nets
- There’s More To Machine Learning Than CNNson June 9, 2021 at 12:01 am
Different learning structures provide optimizations based on variables such as time, accuracy, and what's considered important in the data.
- omniQ Receives Contract to Deploy AI Based Technology at Philadelphia International Airporton June 8, 2021 at 6:02 am
Q’s AI Based EZ Edge™ VRS (Vehicle Recognition System) automates and monitors entry and exits of vehicles to regulate and facilitate ride share traffic and ease congestion. EZ Edge™ will be deployed ...
- The rush to commercialize AI is creating major security riskson June 8, 2021 at 12:20 am
Researchers from the University of Maryland presented an attack technique meant to slow down deep learning models that have been optimized for fast and sensitive operations.
- MIT puts ICs and a network inside a sewable fibreon June 7, 2021 at 10:17 am
Researchers at MIT have made a fibre containing integrated circuits and a wired network that can be sewn into fabrics and survive at least 10 washing cycle ...
- Artificial intelligence spots coronal holes to automate space weather predictionon June 7, 2021 at 7:47 am
Skoltech and their colleagues from the US and Germany have developed a new neural network that can reliably detect coronal holes from space-based observations. This application paves the way for more ...