SAN FRANCISCO, Nov. 20, 2020 /PRNewswire/ -- Fyusion, which enables the creation of beautiful 3D images with deep AI understanding, today announced it has been selected to present new research findings at the annual SIGGRAPH Asia conference on Dec. 4-13.
Due to the coronavirus pandemic, the 13th ACM SIGGRAPH Conference and Exhibition on Computer Graphics and Interactive Techniques will be held as a fully virtual event this year, after originally being scheduled for Daegu, South Korea.
The event attracts technical and creative people from all over the world who are interested in research, science, and emerging technologies related to art, animation, gaming, interactivity, and education. This year's conference will feature more than 8,000 attendees and 700 speakers.
Fyusion team members will present three scientific posters focused on research which makes innovative use of multi-view imagery that is captured with a basic consumer smartphone to visualize 3D data in a photorealistic manner.
Fyusion's scientific authors include Srinivas Rao, Research Engineer; Yusuke Tomoto, Senior Research Engineer; Rodrigo Ortiz-Cayon, Lead Research Scientist; Aidas Liaudanskas, Senior Machine Learning Engineer; Krunal Chande, Head of Computer Vision 3D Reconstruction; and Fyusion Chief Technology Officer and Co-Founder Stefan Holzer.
"We are proud to present Fyusion's latest research and insights at this prestigious global conference," said Holzer. "We are also grateful to our colleagues at the University of Bath who collaborated closely with Fyusion on all three research projects."
Holzer gave special thanks to computer vision researcher Tobias Bertel and Assistant Professor Christian Richardt of the University of Bath for their UK-based school's important contributions to the project.
Srinivas Rao began his Fyusion career as an intern, and previous Fyusion Siggraph presenters also began as interns, who like Rao later became full-time employees.
"Fyusion has always placed a huge emphasis on professional development, and providing talented young researchers with opportunities to challenge themselves and fulfill their potential," said Ortiz-Cayon. "Presenting at SIGGRAPH is an exciting opportunity for all of us, and it's especially rewarding to see the years-long commitments of our interns—which grew into full-time roles for them—recognized by our peers at a global conference."
Fyusion's posters at the conference will include:
Deferred Neural Rendering for View Extrapolation – Image-based rendering methods that support visually pleasing surface reflections require accurate surface geometries and large amounts of input images. While using a casually captured circular video sweep as input, we extend Deferred Neural Rendering to extrapolate smooth viewpoints around objects like a car.
Free-Viewpoint Facial Reenactment from a Casual Capture – We propose a system for free-viewpoint facial reenactment from a casual video capture of a target subject. Our system renders and reenacts the subject consistently in all the captured views. The reenactment of the target subject is driven by an expression sequence of a source subject, which is captured using a custom app running on an iPhone X.
Casual Real-World VR using Light Fields – We believe that virtual reality (VR) would benefit from more end-to-end systems centered around a casual capturing procedure, high-quality visual results, and representations that are viewable on multiple target platforms. We present an end-to-end system that is designed for casual creation of real-world VR content, using only a smartphone to obtain color images.
About Fyusion Inc.
At the intersection of artificial intelligence and 3D imaging, there is immeasurable potential for enterprises to improve how people live and work. Fyusion Inc. opens the possibilities of AI-driven 3D imaging by making these cutting-edge technologies accessible to enterprises. With over 135 patents, we build next-generation applications with a focus on the automotive, vehicle inspections, and e-commerce industries. For more information, visit www.Fyusion.com. Or, follow us on LinkedIn or Twitter.