A Survey on Deep Learning Techniques for Stereo-Based Depth Estimation

Laga, Hamid; Jospin, Laurent Valentin; Boussaid, Farid; Bennamoun, Mohammed

doi:10.1109/tpami.2020.3032602

Cited by 193 publications

(75 citation statements)

References 138 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…While some work has been done in terms of comparative study of depth estimation methods for either stereo or monocular camera, few work features a comparative study of both monocular and stereo. [27] and [28] present a comprehensive survey of stereo-based depth estimation as well as an in-depth evaluation of the methods. [29] offers a new set of evaluation protocols devoted to single image depth estimation in order to better assess the performance of the proposed methods.…”

Section: Evaluation Of Depth Estimation Methodsmentioning

confidence: 99%

A Comparative Study of Deep Learning-based Depth Estimation Approaches: Application to Smart Mobility

Mauri

Khemmar

Decoux

et al. 2021

2021 8th International Conference on Smart Computing and Communications (ICSCC)

View full text Add to dashboard Cite

Section: Evaluation Of Depth Estimation Methodsmentioning

confidence: 99%

A Comparative Study of Deep Learning-based Depth Estimation Approaches: Application to Smart Mobility

Mauri

Khemmar

Decoux

et al. 2021

2021 8th International Conference on Smart Computing and Communications (ICSCC)

View full text Add to dashboard Cite

“…Passive methods are less accurate but have fewer constraints and are cheaper. Passive methods can be roughly divided into two subcategories, according to the hardware devices: stereo-based [27], in which a couple of calibrated or uncalibrated cameras are used to shoot a scene from two different points of view, and monocular [28], in which depth information is extracted by a single image. Some of the newest approaches use deep neural networks on monocular images [29][30][31][32][33][34].…”

Section: Depth Estimationmentioning

confidence: 99%

A Dataset of Annotated Omnidirectional Videos for Distancing Applications

et al. 2021

View full text Add to dashboard Cite

Omnidirectional (or 360°) cameras are acquisition devices that, in the next few years, could have a big impact on video surveillance applications, research, and industry, as they can record a spherical view of a whole environment from every perspective. This paper presents two new contributions to the research community: the CVIP360 dataset, an annotated dataset of 360° videos for distancing applications, and a new method to estimate the distances of objects in a scene from a single 360° image. The CVIP360 dataset includes 16 videos acquired outdoors and indoors, annotated by adding information about the pedestrians in the scene (bounding boxes) and the distances to the camera of some points in the 3D world by using markers at fixed and known intervals. The proposed distance estimation algorithm is based on geometry facts regarding the acquisition process of the omnidirectional device, and is uncalibrated in practice: the only required parameter is the camera height. The proposed algorithm was tested on the CVIP360 dataset, and empirical results demonstrate that the estimation error is negligible for distancing applications.

show abstract

“…They applied their technique to inpainting for both binocular and multi-view stereo pipelines, and they demonstrated that dense 3D models of higher quality are produced by maps refined by their technique. Traditionally, handcrafted approaches have been used for depth map estimation, which suffers from a number of imperfections, i.e., large uniform regions and textured areas and occlusions [122].…”

Section: Image Inpaintingmentioning

confidence: 99%