Deep Video Codec Control for Vision Models
This addresses a critical issue for real-world video processing pipelines that rely on deep vision models, offering a novel solution to maintain model accuracy in bandwidth-limited scenarios.
The paper tackles the problem that standard video codecs, optimized for human perception, degrade deep vision model performance, and presents a learnable deep video codec control that improves vision performance under bandwidth constraints while adhering to standards.
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.