Deep Video Codec Control for Vision Models

arXiv:2308.16215v5 Announce Type: replace-cross
Abstract: Standardized lossy video coding is at the core of almost all real-world video processing pipelines. Rate control is used to enable standard codecs to adapt to different network bandwidth conditions or storage constraints. However, standard video codecs (e.g., H.264) and their rate control modules aim to minimize video distortion w.r.t human quality assessment. We demonstrate empirically that standard-coded videos vastly deteriorate the performance of deep vision models. To overcome the deterioration of vision performance, this …

abstract adapt aim arxiv bandwidth codec coding constraints control core cs.cv cs.lg cs.mm eess.iv modules network pipelines processing rate standard storage type video video processing vision vision models world