Investigating the Impact of Various Loss Functions and Learnable Wiener Filter for Laparoscopic Image Desmoking
This work addresses the problem of improving image quality in laparoscopic surgery for medical professionals, but it is incremental as it focuses on analyzing an existing framework rather than introducing new methods.
This paper conducted an ablation study on the ULW framework for laparoscopic image desmoking, systematically removing components like the learnable Wiener filter and individual loss terms to evaluate their contributions, with results benchmarked on a public dataset using metrics such as SSIM, PSNR, MSE, and CIEDE-2000.
To rigorously assess the effectiveness and necessity of individual components within the recently proposed ULW framework for laparoscopic image desmoking, this paper presents a comprehensive ablation study. The ULW approach combines a U-Net based backbone with a compound loss function that comprises mean squared error (MSE), structural similarity index (SSIM) loss, and perceptual loss. The framework also incorporates a differentiable, learnable Wiener filter module. In this study, each component is systematically ablated to evaluate its specific contribution to the overall performance of the whole framework. The analysis includes: (1) removal of the learnable Wiener filter, (2) selective use of individual loss terms from the composite loss function. All variants are benchmarked on a publicly available paired laparoscopic images dataset using quantitative metrics (SSIM, PSNR, MSE and CIEDE-2000) alongside qualitative visual comparisons.