Rethinking the Elementary Function Fusion for Single-Image Dehazing
It addresses image quality issues in dehazing for computer vision applications, but appears incremental as it builds on the DM2F model.
This paper tackles limitations in physical models for single-image dehazing by proposing the CL2S network, which replaces a logarithmic function with a trigonometric model to better fit haze distribution, achieving outstanding performance on multiple datasets with improved detail and color authenticity.
This paper addresses the limitations of physical models in the current field of image dehazing by proposing an innovative dehazing network (CL2S). Building on the DM2F model, it identifies issues in its ablation experiments and replaces the original logarithmic function model with a trigonometric (sine) model. This substitution aims to better fit the complex and variable distribution of haze. The approach also integrates the atmospheric scattering model and other elementary functions to enhance dehazing performance. Experimental results demonstrate that CL2S achieves outstanding performance on multiple dehazing datasets, particularly in maintaining image details and color authenticity. Additionally, systematic ablation experiments supplementing DM2F validate the concerns raised about DM2F and confirm the necessity and effectiveness of the functional components in the proposed CL2S model. Our code is available at \url{https://github.com/YesianRohn/CL2S}, where the corresponding pre-trained models can also be accessed.