Abstract

As one of the key requirements for underwater exploration, underwater depth map estimation is of great importance in underwater vision research. Although significant progress has been achieved in the fields of image-to-image translation and depth map estimation, a gap between normal depth map estimation and underwater depth map estimation still remains. Additionally, it is a great challenge to build a mapping function that converts a single underwater image into an underwater depth map due to the lack of paired data. Moreover, the ever-changing underwater environment further intensifies the difficulty of finding an optimal mapping solution. To eliminate these bottlenecks, we developed a novel image-to-image framework for underwater image synthesis and depth map estimation in underwater conditions. For the problem of the lack of paired data, by translating hazy in-air images (with a depth map) into underwater images, we initially obtained a paired dataset of underwater images and corresponding depth maps. To enrich our synthesized underwater dataset, we further translated hazy in-air images into a series of continuously changing underwater images with a specified style. For the depth map estimation, we included a coarse-to-fine network to provide a precise depth map estimation result. We evaluated the efficiency of our framework for a real underwater RGB-D dataset. The experimental results show that our method can provide a diversity of underwater images and the best depth map estimation precision.

Highlights

  • In 3D computer vision, a depth map refers to a frame in which each pixel represents the distances of the surfaces of objects in a scene from a viewpoint

  • In order to solve these problems, we propose a novel image-to-image translation framework for underwater image synthesis and depth map estimation

  • Our overall framework consists of three generators, namely, Gu : ( x, d, cy, z) → ỹ, Gd1 : ỹ → d1, and Gd2 : (ỹ, d1 ) → d2, where x represents the original in-air images, d is the corresponding depth map, cy is the target underwater domain, z is the continuous noise vector, ỹ is the generated underwater image, d1 represents the global results of the underwater depth map estimation, and d2 is the final estimated depth map

Read more

Summary

Introduction

In 3D computer vision, a depth map refers to a frame in which each pixel represents the distances of the surfaces of objects in a scene from a viewpoint. There are a number of uses for depth maps, including machine vision, 3D reconstruction, and shadow mapping [1]. As an important branch of underwater vision, underwater depth map estimation plays an important role in many fields, including underwater landform surveys, vehicle navigation, and underwater hull cleaning. Some in-air depth map estimation devices, such as the Kinect [5], Lidar [6], or monocular lenses [7], can only obtain a limited effect in an underwater environment [8]. Inhomogeneous illumination further intensifies the problem of color distortion in underwater images

Methods
Results
Discussion
Conclusion
Full Text
Published version (Free)

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call