Feedback-Driven Rate Control for Learned Video Compression

2026-04-21

AI Summary

This work addresses the lack of stable dynamic bitrate control in existing learned video compression methods under target bitrate and budget constraints. The authors propose a feedback-driven closed-loop rate control framework built upon the DCVC architecture, featuring a single-model multi-bitrate interface that enables continuous bitrate modulation via the λ parameter. The approach innovatively integrates a logarithmic-domain PI/PID controller with a dual-branch GRU regulator: the former dynamically adjusts λ online to track the target bitrate, while the latter optimizes frame-level bit allocation based on causal coding statistics. Experimental results demonstrate that the method achieves average bitrate errors as low as 2.13%–2.24% on the UVG and HEVC datasets, with BD-rate reductions of 5.69% and 4.49%, respectively, significantly enhancing both bitrate controllability and rate-distortion performance.

Technology Category

• Computer Vision: Learning & Optimization for CV
• Search and Optimization: Learning to Search
• Intelligent Robots: Behavior Learning & Control

Application Category

• Economics, Online Markets and Human Computation: LLM based quality controls for crowd work
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs

Abstract

End-to-end learned video compression has achieved strong rate-distortion performance, but rate control remains underexplored, especially in target-bitrate-driven and budget-constrained scenarios. Existing methods mainly rely on explicit R-D-lambda modeling or feed-forward prediction, which may lack stable online adjustment when video content varies dynamically. We propose a feedback-driven rate control framework for learned video compression. First, we build a single-model multi-rate coding interface on top of a DCVC-style framework, enabling continuous bitrate control through the rate-distortion parameter lambda. Then, a log-domain PI/PID closed-loop controller updates lambda online according to the error between the target bitrate and the entropy-estimated bitrate, achieving stable target bitrate tracking. To further improve frame-level bit allocation under budget constraints, we introduce a dual-branch GRU-based adjustment controller that refines the base control signal using budget-state features and causal coding statistics. Experiments on UVG and HEVC show that the proposed PI/PID controller achieves average bitrate errors of 2.88% and 2.95% on DCVC and DCVC-TCM, respectively. With the proposed adjustment controller, the method further achieves average BD-rate reductions of 5.69% and 4.49%, while reducing the average bitrate errors to 2.13% and 2.24%. These results show that the proposed method provides a practical solution for learned video compression with both controllable bitrate and improved rate-distortion performance.

Problem

• learned video compression
• rate control
• bitrate constraint
• target bitrate
• online adjustment

Innovation

• feedback-driven rate control
• learned video compression
• PID controller
• bit allocation
• multi-rate coding