Date: Wednesday, May 15, 2019
Time: Food/Drink/Social: 6:00 pm
Meeting Start Time: 6:30 pm
Location: AJA Video
180 Litton Dr.
Grass Valley, CA 95945
Contact: Bill Bowen 530-559-4118
Speakers: Thomas, “Da Expert” True, Senior Applied Engineer, NVIDIA Professional Visualization Group
Andrew “The Stand-in” Page, Advanced Technologies Group Manager, NVIDIA Professional Visualization Group
Deep Learning for Slow Motion Video
No longer simply the subject of research, Deep Learning (DL), a powerful branch of Artificial Intelligence (AI), is finding applications in the video production pipeline. Applications are already accelerating labor intensive tasks and giving time and control back to creative professionals. This presentation will provide an introduction to deep learning and its applications in media production, then dive into an application of deep learning to create slow motion video with a focus on both what is possible today, and some caveats and pitfalls as the technology moves into the future. A video clip appears to slow down by generating and inserting intermediate frames between two consecutive frames, making sure that the inserted frames are spatially and temporally coherent. While traditional methods implement single-frame interpolation, we will present how a DL network can be trained to perform variable-length multi-frame video interpolation where both the motion interpretation and occlusion reasoning are jointly modeled.
Thomas True is a Senior Applied Engineer for Professional Video and Image Processing in NVIDIA’s Professional Visualization Group where he focuses on the use of GPUs in broadcast, video and film applications ranging from pre-visualization to post production and live to air. Prior to joining NVIDIA, Tom was an Applications Engineering at SGI. Thomas has a M.S. degree in Computer Science from the Graphics Lab at Brown University and a B.S. Degree from the Rochester Institute of Technology.
Andrew Page Manages the Advanced Technologies Group in NVIDIA’s Professional Visualization group. He manages technologies in a wide range of fields including 8K Video, 3D Printing, Voxel processing and DCC workflows. His career has spanned marketing and engineering jobs across professional photo imaging, color Management and 3D Graphics. He holds a degree in computer science from the University of California at Davis.
Light refreshments will be provided by AJA Video.
Non-members and guests are welcome to attend. SMPTE annual memberships are available on-line (https://www.smpte.org/join) and start at $75 for an individual and $15 for students.
For questions about this meeting, please contact any Section officer.
We hope to see you there.