Saved in:
Bibliographic Details
Main Authors: Fang, Zining, Xue, Cheng, Liu, Chunhui, Xu, Bin, Chen, Ming, Hu, Xiaowei
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2603.22844
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913090101051392
author Fang, Zining
Xue, Cheng
Liu, Chunhui
Xu, Bin
Chen, Ming
Hu, Xiaowei
author_facet Fang, Zining
Xue, Cheng
Liu, Chunhui
Xu, Bin
Chen, Ming
Hu, Xiaowei
contents Surgical smoke severely degrades intraoperative video quality, obscuring anatomical structures and limiting surgical perception. Existing learning-based desmoking approaches rely on scarce paired supervision and deterministic restoration pipelines, making it difficult to perform exploration or reinforcement-driven refinement under real surgical conditions. We propose PhySe-RPO, a diffusion restoration framework optimized through Physics- and Semantics-Guided Relative Policy Optimization. The core idea is to transform deterministic restoration into a stochastic policy, enabling trajectory-level exploration and critic-free updates via group-relative optimization. A physics-guided reward imposes illumination and color consistency, while a visual-concept semantic reward learned from CLIP-based surgical concepts promotes smoke-free and anatomically coherent restoration. Together with a reference-free perceptual constraint, PhySe-RPO produces results that are physically consistent, semantically faithful, and clinically interpretable across synthetic and real robotic surgical datasets, providing a principled route to robust diffusion-based restoration under limited paired supervision.
format Preprint
id arxiv_https___arxiv_org_abs_2603_22844
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle PhySe-RPO: Physics and Semantics Guided Relative Policy Optimization for Diffusion-Based Surgical Smoke Removal
Fang, Zining
Xue, Cheng
Liu, Chunhui
Xu, Bin
Chen, Ming
Hu, Xiaowei
Artificial Intelligence
Surgical smoke severely degrades intraoperative video quality, obscuring anatomical structures and limiting surgical perception. Existing learning-based desmoking approaches rely on scarce paired supervision and deterministic restoration pipelines, making it difficult to perform exploration or reinforcement-driven refinement under real surgical conditions. We propose PhySe-RPO, a diffusion restoration framework optimized through Physics- and Semantics-Guided Relative Policy Optimization. The core idea is to transform deterministic restoration into a stochastic policy, enabling trajectory-level exploration and critic-free updates via group-relative optimization. A physics-guided reward imposes illumination and color consistency, while a visual-concept semantic reward learned from CLIP-based surgical concepts promotes smoke-free and anatomically coherent restoration. Together with a reference-free perceptual constraint, PhySe-RPO produces results that are physically consistent, semantically faithful, and clinically interpretable across synthetic and real robotic surgical datasets, providing a principled route to robust diffusion-based restoration under limited paired supervision.
title PhySe-RPO: Physics and Semantics Guided Relative Policy Optimization for Diffusion-Based Surgical Smoke Removal
topic Artificial Intelligence
url https://arxiv.org/abs/2603.22844