Reinforcement Learning for SAR View Angle Inversion with Differentiable SAR Renderer

TL;DR

This paper introduces a deep reinforcement learning framework with a differentiable SAR renderer to accurately invert SAR view angles, overcoming data scarcity and background interference issues, and demonstrating robustness on simulated and real datasets.

Contribution

The paper presents a novel interactive DRL approach with a differentiable SAR renderer for precise view angle inversion in SAR images, addressing data scarcity and background interference.

Findings

Outperforms existing methods on simulated datasets

Effective in cross-domain scenarios with real data

Enhances sensitivity to fine-grained view angle variations

Abstract

The electromagnetic inverse problem has long been a research hotspot. This study aims to reverse radar view angles in synthetic aperture radar (SAR) images given a target model. Nonetheless, the scarcity of SAR data, combined with the intricate background interference and imaging mechanisms, limit the applications of existing learning-based approaches. To address these challenges, we propose an interactive deep reinforcement learning (DRL) framework, where an electromagnetic simulator named differentiable SAR render (DSR) is embedded to facilitate the interaction between the agent and the environment, simulating a human-like process of angle prediction. Specifically, DSR generates SAR images at arbitrary view angles in real-time. And the differences in sequential and semantic aspects between the view angle-corresponding images are leveraged to construct the state space in DRL, which effectively suppress the complex background interference, enhance the sensitivity to temporal variations, and improve the capability to capture fine-grained information. Additionally, in order to maintain the stability and convergence of our method, a series of reward mechanisms, such as memory difference, smoothing and boundary penalty, are utilized to form the final reward function. Extensive experiments performed on both simulated and real datasets demonstrate the effectiveness and robustness of our proposed method. When utilized in the cross-domain area, the proposed method greatly mitigates inconsistency between simulated and real domains, outperforming reference methods significantly.