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:
- ‘Augmented reality’ comes to the job siteon September 30, 2020 at 5:00 pm
This led to intense study of the means and methods to solve the problem. We used 4D visualization and augmented reality tools to plan and communicate the work with the labor crews. While the 4D ...
- Magnetic resonance in medical scienceson September 20, 2020 at 5:01 pm
4D Flow MR Imaging Reveals a Decrease of Left Atrial Blood Flow in a Patient with Cardioembolic Cerebral Infarction after Pulmonary Left Upper Lobectomy. Confirmation of Age-dependence in the ...
- Fully Automatic Analysis of Cardiac Function on MRIs from Siemenson September 14, 2020 at 5:00 pm
Furthermore, Siemens has developed Argus 4D VF for the four-dimensional visualization of the cardiac function. This software enables the visualization and analysis of heart function disorders ...
- Texas Cardiac Arrhythmia Institute physicians participate in clinical trial for 4D imaging technology for complex heart procedureson August 31, 2020 at 2:09 am
"4D imaging provides a high-resolution view ... appendage closures and cardiac ablation procedures. This enhanced visualization allows physicians to better assess complex cardiac structures ...
- Texas Cardiac Arrhythmia Institute physicians participate in clinical trial for 4D imaging technology for complex heart procedureson August 30, 2020 at 7:56 pm
"4D imaging provides a high-resolution view of the heart structure ... appendage closures and cardiac ablation procedures. This enhanced visualization allows physicians to better assess complex ...
Go deeper with Google Headlines on:
Go deeper with Bing News on:
Convolutional neural nets
- COM Express module supports PCIe Gen4 and AI optimizationon September 25, 2020 at 6:37 am
ADLINK Technology, a global provider of leading edge computing solutions, launches its next generation COM Express Type 6 module, the cExpress-TL, based on the 11th Gen Intel® Core™ i7/i5/i3 and ...
- How AI Scratches More Than Just the Surface in Neurodegenerationon September 25, 2020 at 5:00 am
The researchers have used Artificial intelligence to identify and categorize neural degeneration in the model organism C. elegans.
- Google’s Geoff Hinton And His Team File A Patent For Capsule Neural Networkson September 25, 2020 at 4:41 am
Capsule networks are aimed at alleviating the extra dimensionality which surfaces with a convolutional neural network.
- BrainChip confirms validation of its Akida neural processoron September 24, 2020 at 4:49 pm
BrainChip, a provider of ultra-low power AI technology, has announced that the validation of its Akida Neuromorphic System-on-Chip (NSoC) design with functional silicon. The Akida NSoC is an ...
- BrainChip Confirms Validation of the Akida Neural Processoron September 17, 2020 at 1:40 pm
The cores can be implemented for either convolutional layers or fully ... The event-based neural network processor is inspired by the spiking nature of the human brain and is implemented in ...