Scaling Neural Face Synthesis to High FPS and Low Latency by Neural Caching. (arXiv:2211.05773v1 [cs.CV])

Recent neural rendering approaches greatly improve image quality, reaching
near photorealism. However, the underlying neural networks have high runtime,
precluding telepresence and virtual reality applications that require high
resolution at low latency. The sequential dependency of layers in deep networks
makes their optimization difficult. We break this dependency by caching
information from the previous frame to speed up the processing of the current
one with an implicit warp. The warping with a shallow network reduces latency
and the caching operations …

arxiv caching face latency low scaling