# Neural Frank-Wolfe Policy Optimization for Region-of-Interest Intra-Frame Coding with HEVC/H.265

arXiv: https://arxiv.org/abs/2209.13210 · HTML: https://mlsanity.com/paper/2209.13210/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 6 of its 11 references that are in the map.
- First posted on arXiv 27 Sep 2022.

## Builds on (most cited first, 6 of 6)

- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [The 2017 DAVIS Challenge on Video Object Segmentation](https://mlsanity.com/paper/1704.00675/) (2017)
- [Safe Exploration in Continuous Action Spaces](https://mlsanity.com/paper/1801.08757/) (2018)
- [Task-driven Semantic Coding via Reinforcement Learning](https://mlsanity.com/paper/2106.03511/) (2021)
- [Escaping from Zero Gradient: Revisiting Action-Constrained Reinforcement Learning via Frank-Wolfe Policy Optimization](https://mlsanity.com/paper/2102.11055/) (2021)
- [A Dual-Critic Reinforcement Learning Framework for Frame-level Bit Allocation in HEVC/H.265](https://mlsanity.com/paper/2104.01735/) (2021)

## Built on by (most cited first, 1 of 1)

- [RL-RC-DoT: A Block-level RL agent for Task-Aware Video Compression](https://mlsanity.com/paper/2501.12216/) (2025)

## Abstract (arXiv)

This paper presents a reinforcement learning (RL) framework that utilizes Frank-Wolfe policy optimization to solve Coding-Tree-Unit (CTU) bit allocation for Region-of-Interest (ROI) intra-frame coding. Most previous RL-based methods employ the single-critic design, where the rewards for distortion minimization and rate regularization are weighted by an empirically chosen hyper-parameter. Recently, the dual-critic design is proposed to update the actor by alternating the rate and distortion critics. However, its convergence is not guaranteed. To address these issues, we introduce Neural Frank-Wolfe Policy Optimization (NFWPO) in formulating the CTU-level bit allocation as an action-constrained RL problem. In this new framework, we exploit a rate critic to predict a feasible set of actions. With this feasible set, a distortion critic is invoked to update the actor to maximize the ROI-weighted image quality subject to a rate constraint. Experimental results produced with x265 confirm the superiority of the proposed method to the other baselines.