Dehazing Cost Volume for Deep Multi-view Stereo in Scattering Media with Airlight and Scattering Coefficient Estimation
This work addresses the challenge of accurate 3D reconstruction for MVS systems operating in adverse scattering conditions, which is a problem for autonomous navigation and environmental monitoring.
This paper introduces a learning-based multi-view stereo (MVS) method for scattering media like fog or smoke, utilizing a novel 'dehazing cost volume' to address the depth-dependent image degradation. It also proposes a method for estimating scattering parameters such as airlight and scattering coefficients, which are geometrically optimized using a sparse 3D point cloud. Experiments on synthesized hazy images show the effectiveness of their dehazing cost volume compared to ordinary cost volumes in scattering media.
We propose a learning-based multi-view stereo (MVS) method in scattering media, such as fog or smoke, with a novel cost volume, called the dehazing cost volume. Images captured in scattering media are degraded due to light scattering and attenuation caused by suspended particles. This degradation depends on scene depth; thus, it is difficult for traditional MVS methods to evaluate photometric consistency because the depth is unknown before three-dimensional (3D) reconstruction. The dehazing cost volume can solve this chicken-and-egg problem of depth estimation and image restoration by computing the scattering effect using swept planes in the cost volume. We also propose a method of estimating scattering parameters, such as airlight, and a scattering coefficient, which are required for our dehazing cost volume. The output depth of a network with our dehazing cost volume can be regarded as a function of these parameters; thus, they are geometrically optimized with a sparse 3D point cloud obtained at a structure-from-motion step. Experimental results on synthesized hazy images indicate the effectiveness of our dehazing cost volume against the ordinary cost volume regarding scattering media. We also demonstrated the applicability of our dehazing cost volume to real foggy scenes.