Reliable Image Dehazing by NeRF
This addresses image quality degradation due to haze for applications like photography and computer vision, representing a novel method for a known bottleneck.
The paper tackles image dehazing by proposing a new model combining optical scattering and computer graphics lighting rendering, which reconstructs 3D space to accurately calculate and remove haze without training data. The method achieves a 4 dB higher quality average scene than other approaches, with more natural colors and robustness across scenarios.
We present an image dehazing algorithm with high quality, wide application, and no data training or prior needed. We analyze the defects of the original dehazing model, and propose a new and reliable dehazing reconstruction and dehazing model based on the combination of optical scattering model and computer graphics lighting rendering model. Based on the new haze model and the images obtained by the cameras, we can reconstruct the three-dimensional space, accurately calculate the objects and haze in the space, and use the transparency relationship of haze to perform accurate haze removal. To obtain a 3D simulation dataset we used the Unreal 5 computer graphics rendering engine. In order to obtain real shot data in different scenes, we used fog generators, array cameras, mobile phones, underwater cameras and drones to obtain haze data. We use formula derivation, simulation data set and real shot data set result experimental results to prove the feasibility of the new method. Compared with various other methods, we are far ahead in terms of calculation indicators (4 dB higher quality average scene), color remains more natural, and the algorithm is more robust in different scenarios and best in the subjective perception.