Deep Video Codec Control for Vision Models

Publication Date: 6/17/2024

Event: AIS: Vision, Graphics and AI for Streaming Workshop at CVPR 2024

Reference: pp. 5732-5741, 2024

Authors: Christoph Reich, NEC Laboratories America, Inc., Technische Universitat Darmstadt, Germany; Biplob Debnath, NEC Laboratories America, Inc.; Deep Patel, NEC Laboratories America, Inc.; Tim Prangemeier, Technische Universitat Darmstadt, Germany; Srimat T. Chakradhar, NEC Laboratories America, Inc.

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.

Publication Link: