Generative Smoke Removal

Oleksii Sidorov, Congcong Wang, Faouzi Alaya Cheikh
; Proceedings of the Machine Learning for Health NeurIPS Workshop, PMLR 116:81-92, 2020.

Abstract

In minimally invasive surgery, the use of tissue dissection tools causes smoke, which inevitably degrades the image quality. This could reduce the visibility of the operation field for surgeons and introduces errors for the computer vision algorithms used in surgical navigation systems. In this paper, we propose a novel approach for computational smoke removal using supervised image-to-image translation. We demonstrate that straightforward application of existing generative algorithms allows removing smoke but decreases image quality and introduces synthetic noise (grid-structure). Thus, we propose to solve this issue by modification of GAN’s architecture and adding perceptual image quality metric to the loss function. Obtained results demonstrate that proposed method efficiently removes smoke as well as preserves perceptually sufficient image quality.

Cite this Paper


BibTeX
@InProceedings{pmlr-v116-sidorov20a, title = {{Generative Smoke Removal}}, author = {Sidorov, Oleksii and Wang, Congcong and Cheikh, Faouzi Alaya}, booktitle = {Proceedings of the Machine Learning for Health NeurIPS Workshop}, pages = {81--92}, year = {2020}, editor = {Adrian V. Dalca and Matthew B.A. McDermott and Emily Alsentzer and Samuel G. Finlayson and Michael Oberst and Fabian Falck and Brett Beaulieu-Jones}, volume = {116}, series = {Proceedings of Machine Learning Research}, address = {}, month = {13 Dec}, publisher = {PMLR}, pdf = {http://proceedings.mlr.press/v116/sidorov20a/sidorov20a.pdf}, url = {http://proceedings.mlr.press/v116/sidorov20a.html}, abstract = {In minimally invasive surgery, the use of tissue dissection tools causes smoke, which inevitably degrades the image quality. This could reduce the visibility of the operation field for surgeons and introduces errors for the computer vision algorithms used in surgical navigation systems. In this paper, we propose a novel approach for computational smoke removal using supervised image-to-image translation. We demonstrate that straightforward application of existing generative algorithms allows removing smoke but decreases image quality and introduces synthetic noise (grid-structure). Thus, we propose to solve this issue by modification of GAN’s architecture and adding perceptual image quality metric to the loss function. Obtained results demonstrate that proposed method efficiently removes smoke as well as preserves perceptually sufficient image quality.} }
Endnote
%0 Conference Paper %T Generative Smoke Removal %A Oleksii Sidorov %A Congcong Wang %A Faouzi Alaya Cheikh %B Proceedings of the Machine Learning for Health NeurIPS Workshop %C Proceedings of Machine Learning Research %D 2020 %E Adrian V. Dalca %E Matthew B.A. McDermott %E Emily Alsentzer %E Samuel G. Finlayson %E Michael Oberst %E Fabian Falck %E Brett Beaulieu-Jones %F pmlr-v116-sidorov20a %I PMLR %J Proceedings of Machine Learning Research %P 81--92 %U http://proceedings.mlr.press %V 116 %W PMLR %X In minimally invasive surgery, the use of tissue dissection tools causes smoke, which inevitably degrades the image quality. This could reduce the visibility of the operation field for surgeons and introduces errors for the computer vision algorithms used in surgical navigation systems. In this paper, we propose a novel approach for computational smoke removal using supervised image-to-image translation. We demonstrate that straightforward application of existing generative algorithms allows removing smoke but decreases image quality and introduces synthetic noise (grid-structure). Thus, we propose to solve this issue by modification of GAN’s architecture and adding perceptual image quality metric to the loss function. Obtained results demonstrate that proposed method efficiently removes smoke as well as preserves perceptually sufficient image quality.
APA
Sidorov, O., Wang, C. & Cheikh, F.A.. (2020). Generative Smoke Removal. Proceedings of the Machine Learning for Health NeurIPS Workshop, in PMLR 116:81-92

Related Material