RL-RC-DoT: A Block-level RL agent for Task-Aware Video Compression

TL;DR

This paper introduces a block-level reinforcement learning agent that optimizes video compression for specific downstream tasks like object detection, improving task performance at given bit rates without needing task info during inference.

Contribution

It presents a novel RL-based method for controlling macro-block QPs to optimize task-specific video encoding, compatible with standard encoders and suitable for streaming and edge devices.

Findings

Significant improvements in car detection accuracy at fixed bit rates.

Enhanced ROI encoding performance compared to traditional methods.

Policy does not require downstream task input during inference.

Abstract

Video encoders optimize compression for human perception by minimizing reconstruction error under bit-rate constraints. In many modern applications such as autonomous driving, an overwhelming majority of videos serve as input for AI systems performing tasks like object recognition or segmentation, rather than being watched by humans. It is therefore useful to optimize the encoder for a downstream task instead of for perceptual image quality. However, a major challenge is how to combine such downstream optimization with existing standard video encoders, which are highly efficient and popular. Here, we address this challenge by controlling the Quantization Parameters (QPs) at the macro-block level to optimize the downstream task. This granular control allows us to prioritize encoding for task-relevant regions within each frame. We formulate this optimization problem as a Reinforcement Learning (RL) task, where the agent learns to balance long-term implications of choosing QPs on both task performance and bit-rate constraints. Notably, our policy does not require the downstream task as an input during inference, making it suitable for streaming applications and edge devices such as vehicles. We demonstrate significant improvements in two tasks, car detection, and ROI (saliency) encoding. Our approach improves task performance for a given bit rate compared to traditional task agnostic encoding methods, paving the way for more efficient task-aware video compression.