We are pleased to announce that CTO Yiannis Andreopoulos will be presenting at NVIDIA GTC Developer Conference at 8:00 am till 8:25 am on March 23rd 2023 on bridging the gap between “Codec” and “Avatar”.
He will be discussing at length the neural avatar solutions currently needed to overcome these three challenges: reliability at scale, minimal or no offline data capture complexity, and minimal training/inference complexity. He will present some avenues to resolve these by merging neural avatar proposals together with conventional video/3D encoding standards. Such a merger can bridge the gap between traditional “codecs” and photorealistic neural avatars and offer significant runtime and bit-rate efficiency versus all existing work.
Further to this, he will highlight how it can also anchor the rendered output to the physical reality captured by sensors at the sender side, which ensures any scene/person augmentation or reenactment is interpretable and controllable when deployed at scale. He will show a demonstration of results on NVIDIA RTX GPUs and summarize lessons learned, such as the importance of accurate visual quality scoring.
To find out more about this event please click here.