@inproceedings{fe56b5ff15504503bc4a4ea8e31617e8,
title = "Deep Video Codec Control for Vision Models",
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 paper presents the first end-to-end learnable deep video codec control that considers both bandwidth constraints and downstream deep vision performance, while adhering to existing standardization. We demonstrate that our approach better preserves downstream deep vision performance than traditional standard video coding.",
keywords = "Codec, Coding for Machines, Deep Video Codec Control, Deep Vision Models, End-to-end Learning, Rate Control, Self-supervised Learning, Standardization, Video Coding",
author = "Christoph Reich and Biplob Debnath and Deep Patel and Tim Prangemeier and Daniel Cremers and Srimat Chakradhar",
note = "Publisher Copyright: {\textcopyright} 2024 IEEE.; 2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2024 ; Conference date: 16-06-2024 Through 22-06-2024",
year = "2024",
doi = "10.1109/CVPRW63382.2024.00582",
language = "English",
series = "IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops",
publisher = "IEEE Computer Society",
pages = "5732--5741",
booktitle = "Proceedings - 2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2024",
}