Uncertainty-Aware Deep Video Compression with Ensembles

arXiv:2403.19158v1 Announce Type: new
Abstract: Deep learning-based video compression is a challenging task, and many previous state-of-the-art learning-based video codecs use optical flows to exploit the temporal correlation between successive frames and then compress the residual error. Although these two-stage models are end-to-end optimized, the epistemic uncertainty in the motion estimation and the aleatoric uncertainty from the quantization operation lead to errors in the intermediate representations and introduce artifacts in the reconstructed frames. This inherent flaw limits the potential for …

abstract art arxiv compression correlation cs.cv deep learning eess.iv error exploit optical residual stage state temporal type uncertainty video video compression