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:
4D visualization
- Unifying network model links recency and central tendency biases in working memory
Seemingly disparate working memory biases, including short-term serial and contraction biases, may arise from a common mechanism via the interaction of multiple networks, each operating over a ...
- Risk analytics software: should your RIA firm have one?
Since the advent of Big Data, more RIA firms are turning to risk analytics software. Should this be part of your RIA tech stack? Read on to find out ...
- AI in Ultrasound Imaging Market Size Expected to Reach USD 2,001.51 Mn by 2032
The global AI in ultrasound imaging market size is calculated at USD 1,030.69 million in 2024 and is expected to reach around USD 2,001.51 million by 2032, growing at a CAGR of 8.6% from 2023 to 2032.
- Tech-Forward Proposals: From Rings to Lab-Grown Diamonds
Tech has made its way into one of the most traditional symbols of love and commitment: the engagement ring. The… Continue reading Tech-Forward Proposals: From Rings to Lab-Grown Diamonds The post Tech ...
- Evolution and diversity of biomineralized columnar architecture in early Cambrian phosphatic-shelled brachiopods
Columnar architectures, developed in early Cambrian phosphatic-shelled brachiopods, are highly biologically controlled and organic-matrix mediated, which sheds new light on the evolution and ...
Go deeper with Google Headlines on:
4D visualization
[google_news title=”” keyword=”4D visualization” num_posts=”5″ blurb_length=”0″ show_thumb=”left”]
Go deeper with Bing News on:
Convolutional neural nets
- PV module fault detection technique based on convolutional neural network
An international research team has used the convolutional neural network (CNN) deep learning algorithm to identify faults in solar panels. Its work showed the proposed technique has a high degree of ...
- High-speed imaging and AI help us understand how insect wings work
Understanding the hinge mechanics is crucial because this is what makes insects efficient flying creatures. It enables them to fly at impressive speeds relative to their body sizes (some insects can ...
- Intel's Hala Point, the world's largest neuromorphic computer, has 1.15 billion neurons
The Hala Point system's 1,152 Loihi 2 chips enable a total of 1.15 billion artificial neurons, Intel said, "and 128 billion synapses distributed over 140,544 neuromorphic processing cores." That is an ...
- convolutional neural network
In 2018 Google announced a convolutional neural network (CNN) based system which they call the Augmented Reality Microscope (ARM), which would use deep learning and augmented reality (AR ...
- Classical optical neural network exhibits 'quantum speedup'
More information: Yifan Sun et al, Correlated optical convolutional neural network with "quantum speedup", Light: Science & Applications (2024). DOI: 10.1038/s41377-024-01376-7 Provided by TranSpread ...
Go deeper with Google Headlines on:
Convolutional neural nets
[google_news title=”” keyword=”convolutional neural nets” num_posts=”5″ blurb_length=”0″ show_thumb=”left”]