Depth estimation from stereo cameras through a curved transparent medium

Yoon, Seongwook; Choi, Taehyeon; Sull, Sanghoon

doi:10.1016/j.patrec.2019.11.012

Cited by 10 publications

(7 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Agrawal et al have also studied MVS in a refractive medium in [57], but their work remains limited to a (multi-layer) planar interface. To the best of our knowledge, the only work considering a non-planar interface is the recent work of Yoon et al [58]. However, their objective is different, because the curved refractive medium is placed between the observer and the object, while in our case the object lies inside the refractive medium.…”

Section: Related Workmentioning

confidence: 96%

Multi-view stereo of an object immersed in a refractive medium

Bruneau,

Brument,

Calvet

et al. 2024

J. Electron. Imag.

View full text Add to dashboard Cite

In this article we show how to extend the multi-view stereo technique when the object to be reconstructed is inside a transparent -but refractive -medium, which causes distortions in the images. We provide a theoretical formulation of the problem accounting for a general, non-planar shape of the refractive interface, and then a discrete solving method. We also present a pipeline to recover precisely the geometry of the refractive interface, considered as a convex polyhedral object. It is based on the extraction of visible polyhedron vertices from silhouette images and matching across a sequence of images acquired under circular camera motion. These contributions are validated by tests on synthetic and real data.

show abstract

Section: Related Workmentioning

confidence: 96%

Multi-view stereo of an object immersed in a refractive medium

Bruneau,

Brument,

Calvet

et al. 2024

J. Electron. Imag.

View full text Add to dashboard Cite

show abstract

“…Additionally, Pavel et al [4] addressed scenarios with cylinder-shaped transparent shields, using radial basis functions (RBFs) to explicitly model the uneven shield surface. Yoon et al [6] tackled the modeling of stereo camera systems positioned behind curved transparent shields. They parameterized the curved shield and optimized the shape parameters, while also utilizing additional feature points on the inner surface of the shield to effectively estimate its shape.…”

Section: Camera Model Explicitly Models the Ray Pathmentioning

confidence: 99%

“…To address this issue, one method involves estimating light refraction by taking into account the shape of the transparent shield [3][4][5][6]. This method seeks to determine the alteration of light paths as they traverse through the shield, thereby facilitating a more accurate representation of the refracted ray, as depicted on the left side of Figure 1.…”

Section: Introductionmentioning

confidence: 99%

RBF-Based Camera Model Based on a Ray Constraint to Compensate for Refraction Error

Kim,

Yoon

et al. 2023

Sensors

Self Cite

View full text Add to dashboard Cite

A camera equipped with a transparent shield can be modeled using the pinhole camera model and residual error vectors defined by the difference between the estimated ray from the pinhole camera model and the actual three-dimensional (3D) point. To calculate the residual error vectors, we employ sparse calibration data consisting of 3D points and their corresponding 2D points on the image. However, the observation noise and sparsity of the 3D calibration points pose challenges in determining the residual error vectors. To address this, we first fit Gaussian Process Regression (GPR) operating robustly against data noise to the observed residual error vectors from the sparse calibration data to obtain dense residual error vectors. Subsequently, to improve performance in unobserved areas due to data sparsity, we use an additional constraint; the 3D points on the estimated ray should be projected to one 2D image point, called the ray constraint. Finally, we optimize the radial basis function (RBF)-based regression model to reduce the residual error vector differences with GPR at the predetermined dense set of 3D points while reflecting the ray constraint. The proposed RBF-based camera model reduces the error of the estimated rays by 6% on average and the reprojection error by 26% on average.

show abstract

“…Examples of good quality data for this task include Cityscapes and KITTI datasets [11,12]. Among the techniques available for 3D reconstruction and visualization, depth estimation in binocular vision systems, disparity estimation from stereo images and motion parallax estimation from a sequence of images are certainly the most promising techniques for achieving this objective [13,14,15]. In particular, the spatial perception stimulus generated by motion parallax has propelled several theoretical studies in the areas of visual perception and psychology that seek physiological explanations in humans, towards establishing the neurological bases of our visual ability [16,17,18].…”

Section: Output Videomentioning

confidence: 99%

Parallax Motion Effect Generation Through Instance Segmentation And Depth Estimation

Pinto

Cordova

Decker

et al. 2020

2020 IEEE International Conference on Image Processing (ICIP)

View full text Add to dashboard Cite

Stereo vision is a growing topic in computer vision due to the innumerable opportunities and applications this technology offers for the development of modern solutions, such as virtual and augmented reality applications. To enhance the user's experience in threedimensional virtual environments, the motion parallax estimation is a promising technique to achieve this objective. In this paper, we propose an algorithm for generating parallax motion effects from a single image, taking advantage of state-of-the-art instance segmentation and depth estimation approaches. This work also presents a comparison against such algorithms to investigate the trade-off between efficiency and quality of the parallax motion effects, taking into consideration a multi-task learning network capable of estimating instance segmentation and depth estimation at once. Experimental results and visual quality assessment indicate that the PyD-Net network (depth estimation) combined with Mask R-CNN or FBNet networks (instance segmentation) can produce parallax motion effects with good visual quality.

show abstract

Depth estimation from stereo cameras through a curved transparent medium

Cited by 10 publications

References 7 publications

Multi-view stereo of an object immersed in a refractive medium

Multi-view stereo of an object immersed in a refractive medium

RBF-Based Camera Model Based on a Ray Constraint to Compensate for Refraction Error

Parallax Motion Effect Generation Through Instance Segmentation And Depth Estimation

Contact Info

Product

Resources

About