Underwater Stereo Using Refraction-Free Image Synthesized From Light Field Camera

There is a strong demand on capturing underwater scenes without distortions caused by refraction. Since a light field camera can capture several light rays at each point of an image plane from various directions, if geometrically correct rays are chosen, it is possible to synthesize a refraction-free image. In this paper, we propose a novel technique to efficiently select such rays to synthesize a refraction-free image from an underwater image captured by a light field camera. In addition, we propose a stereo technique to reconstruct 3D shapes using a pair of our refraction-free images, which are central projection. In the experiment, we captured several underwater scenes by two light field cameras, synthesized refraction free images and applied stereo technique to reconstruct 3D shapes. The results are compared with previous techniques which are based on approximation, showing the strength of our method.

[1]  Refractive Structure-from-Motion on Underwater Images , 2013, 2013 IEEE International Conference on Computer Vision.

[2]  João Paulo Costeira,et al.  Stereo Reconstruction of a Submerged Scene , 2005, IbPRIA.

[3]  Takashi Matsuyama,et al.  A Pixel-Wise Varifocal Camera Model for Efficient Forward Projection and Linear Extrinsic Calibration of Underwater Cameras with Flat Housings , 2013, 2013 IEEE International Conference on Computer Vision Workshops.

[4]  Ryo Furukawa,et al.  Calibration Technique for Underwater Active Oneshot Scanning System with Static Pattern Projector and Multiple Cameras , 2017, 2017 IEEE Winter Conference on Applications of Computer Vision (WACV).

[5]  Matthew Johnson-Roberson,et al.  Towards real-time underwater 3D reconstruction with plenoptic cameras , 2016, 2016 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS).

[6]  In-So Kweon,et al.  Accurate depth map estimation from a lenslet light field camera , 2015, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[7]  Wei Yang,et al.  Ray Space Features for Plenoptic Structure-from-Motion , 2017, 2017 IEEE International Conference on Computer Vision (ICCV).

[8]  Kiriakos N. Kutulakos,et al.  A Theory of Refractive and Specular 3D Shape by Light-Path Triangulation , 2005, ICCV.

[9]  Tingtian Li,et al.  Robust Reflection Removal Based on Light Field Imaging , 2019, IEEE Transactions on Image Processing.

[10]  Ryo Furukawa,et al.  Multi-scale CNN Stereo and Pattern Removal Technique for Underwater Active Stereo System , 2018, 2018 International Conference on 3D Vision (3DV).

[11]  Michael Bleier,et al.  LOW-COST 3D LASER SCANNING IN AIR ORWATER USING SELF-CALIBRATINGSTRUCTURED LIGHT , 2017 .

[12]  Huimin Lu,et al.  Underwater Light Field Depth Map Restoration Using Deep Convolutional Neural Fields , 2018 .

[13]  Gordon Wetzstein,et al.  Refractive shape from light field distortion , 2011, 2011 International Conference on Computer Vision.

[14]  Visesh Chari,et al.  A theory of multi-layer flat refractive geometry , 2012, 2012 IEEE Conference on Computer Vision and Pattern Recognition.