Optimised ProPainter for Video Diminished Reality Inpainting

TL;DR

This paper presents an optimized zero-shot video inpainting method based on ProPainter, tailored for medical imaging in surgical videos, achieving temporally coherent and detailed reconstructions without training.

Contribution

It introduces a refined ProPainter-based algorithm specifically designed for medical video inpainting, enhancing performance for surgical applications without requiring training.

Findings

Achieves high-quality, temporally coherent inpainting in surgical videos

Operates without training, using optimized parameters and pre-processing

Demonstrates effectiveness through comprehensive evaluation metrics

Abstract

In this paper, part of the DREAMING Challenge - Diminished Reality for Emerging Applications in Medicine through Inpainting, we introduce a refined video inpainting technique optimised from the ProPainter method to meet the specialised demands of medical imaging, specifically in the context of oral and maxillofacial surgery. Our enhanced algorithm employs the zero-shot ProPainter, featuring optimized parameters and pre-processing, to adeptly manage the complex task of inpainting surgical video sequences, without requiring any training process. It aims to produce temporally coherent and detail-rich reconstructions of occluded regions, facilitating clearer views of operative fields. The efficacy of our approach is evaluated using comprehensive metrics, positioning it as a significant advancement in the application of diminished reality for medical purposes.