?
Fast Semi-dense Depth Map Estimation
P. 18-21.
We consider the problem of depth reconstruction from downsampled sparse depth values. We compare our approach with semi-dense depth map interpolation and direct RGB-to-Depth reconstruction solutions on several datasets, including Matterport 3D dataset containing RGB and depth images of 90 building-scale scenes. We demonstrate that the proposed model can produce approximate depth map for over two hundreds images per second.
Publication based on the results of:
In book
NY : Association for Computing Machinery (ACM), 2018
Dmitrii Maslov, Makarov I., , in : Advances in Computational Intelligence: 16th International Work-Conference on Artificial Neural Networks, IWANN 2021, Virtual Event, June 16–18, 2021, Proceedings, Part I. * 1. Vol. 12861.: Springer, 2021. Ch. 38. P. 456-467.
In this paper, we study depth reconstruction via RGB-based, Sparse-Depth, and RGBd approaches. We showed that combination of RGB and Sparse Depth approach in RGBd scenario provides the best results. We also proved that the models performance can be further tuned via proper selection of architecture blocks and number of depth points guiding RGB-to-depth reconstruction. ...
Added: September 1, 2021
Dmitrii Maslov, Makarov I., PeerJ Computer Science 2020 Vol. 6 No. e317 P. 1-22
Autonomous driving highly depends on depth information for safe driving. Recently, major improvements have been taken towards improving both supervised and self-supervised methods for depth reconstruction. However, most of the current approaches focus on single frame depth estimation, where quality limit is hard to beat due to limitations of supervised learning of deep neural networks ...
Added: October 27, 2020
Makarov I., Bakhanova M., Nikolenko S. et al., PeerJ Computer Science 2022 Vol. 8 Article e865
Depth estimation has been an essential task for many computer vision applications, especially in autonomous driving, where safety is paramount. Depth can be estimated not only with traditional supervised learning but also via a self-supervised approach that relies on camera motion and does not require ground truth depth maps. Recently, major improvements have been introduced ...
Added: February 1, 2022
Makarov I., Guschenko-Cheverda I., , in : Proceedings of IEEE 21st International Symposium on Computational Intelligence and Informatics (CINTI'21), 18-20 Nov. 2021. : NY : IEEE, 2021. P. 000115-000120.
Added: January 19, 2022
Nikitin M. Y., Konushin V. S., Konushin A., Computer Optics 2019 Vol. 43 No. 4 P. 618-626
Modern biometric systems based on face recognition demonstrate high recognition quality, but they are vulnerable to face presentation attacks, such as photo or replay attack. Existing face anti-spoofing methods are mostly based on texture analysis and due to lack of training data either use hand-crafted features or fine-tuned pretrained deep models. In this paper we ...
Added: October 31, 2019
Kostenetskiy P., Alkapov R., Chulkevich R. et al., FME Transactions 2019 Vol. 47 No. 4 P. 765-774
Detection and classification of surface defects of the rolled metal is one of the main tasks for correctly assessing product quality. Historically, these tasks were performed by human. But due to a multitude of production factors, such as high rolling rate and temperature of the metal, the results of such human work are rather low. ...
Added: November 22, 2019
Springer, 2022
“Data Analytics and Management in Data Intensive Domains” conference (DAMDID) is planned as a multidisciplinary forum of researchers and practitioners from various domains of science and research promoting cooperation and exchange of ideas in the area of data analysis and management in data intensive domains. Approaches to data analysis and management being developed in specific data intensive domains of X-informatics (such as X = astro, bio, chemo, geo, medicine, neuro, physics, ...
Added: August 30, 2021
Curran Associates, Inc., 2016
CVRP is the premiere annual Computer Vision event comprising the main CVRP conference and 27 co-located workshops and short courses. ...
Added: December 26, 2017
Springer, 2018
The sixteen-volume set comprising the LNCS volumes 11205-11220 constitutes the refereed proceedings of the 15th European Conference on Computer Vision, ECCV 2018, held in Munich, Germany, in September 2018.
The 776 revised papers presented were carefully reviewed and selected from 2439 submissions. The papers are organized in topical sections on learning for vision; computational photography; human analysis; ...
Added: October 30, 2018
Santiago de Chile : IEEE, 2015
Computer Vision (ICCV), 2015 IEEE International Conference on ...
Added: October 19, 2017
Соколова А. И., Konushin A., Programming and Computer Software 2019 Vol. 45 No. 4 P. 213-220
Human gait is an important biometric index that allows to identify a person at a great distance without direct contact. Due to these qualities, which other popular identifiers such as fingerprints or iris do not have, the recognition of a person by the manner of walking has become very common in various areas where video ...
Added: October 31, 2019
Berezovskiy V., Morozov N., , in : The 2nd Workshop and Challenges for Out-of-Distribution Generalization in Computer Vision. ICCV 2023. : [б.и.], 2023.
Knowledge distillation (KD) is a powerful model compression technique broadly used in practical deep learning applications. It is focused on training a small student network to mimic a larger teacher network. While it is widely known that KD can offer an improvement to student generalization in i.i.d setting, its performance under domain shift, i.e. the ...
Added: November 20, 2023
Sawada T., Li Y., Pizlo Z., , in : The Oxford Handbook of Computational and Mathematical Psychology. : Oxford University Press, 2015. P. 255-276.
This chapter provides a review of topics and concepts that are necessary to study and understand 3D shape perception. This includes group theory and their invariants; model-based invariants; Euclidean, affine, and projective geometry; symmetry; inverse problems; simplicity principle; Fechnerian psychophysics; regularization theory; Bayesian inference; shape constancy and shape veridicality; shape recovery; perspective and orthographic projections; ...
Added: March 10, 2015
Ahmed Munna M. T., International Journal of Engineering and Technology 2018 Vol. 7 No. 4 P. 3990-3994
Darkness is the inverse state of the brightness, is obtained as an absence of noticeable light and illumination. Generally, face detection applications cannot detect any human face in a dark image, where the image has captured from the dark environment or dark night. In this manuscript, we demonstrate our experiment, where we use Contrast Stretching, ...
Added: October 29, 2019
Protasov S., Крыловецкий А. А., Кургалин С. Д., Известия ЮФУ. Технические науки 2012 № 6 С. 144-148
This article is devoted to the method of initial image processing to use in stereovision systems. It is based on a modification of video stabilization approach [1]. The method considers image rectification process as a sequence of transformations. Each transformation is found as a solution of optimization problem. The article describes mathematical model that fits ...
Added: October 16, 2017
Tsoy T., Safin R., Magid E. et al., , in : 2022 International Siberian Conference on Control and Communications (SIBCON). : IEEE, 2022. Ch. 9438925.
Camera calibration is one of the important tasks in the field of robotics and computer vision. It enables to increase the accuracy of metric measurements in photogrammetry applications and provides higher performance in computer vision algorithms such as stereo matching and motion estimation. It is known that regardless of the calibration method used variation of ...
Added: October 11, 2021
Springer, 2020
onference, CGI 2020, held in Geneva, Switzerland, in October 2020. The conference was held virtually.
The 43 full papers presented together with 3 short papers were carefully reviewed and selected from 189 submissions. The papers address topics such as: virtual reality; rendering and textures; augmented and mixed reality; video processing; image processing; fluid simulation and control; ...
Added: November 2, 2020
Kononov V., Konushin A., Konushin V., , in : Lecture Notes in Computer Science. Vol. 6835: Pattern Recognition.: Berlin : Springer, 2011. P. 163-172.
We present a new people tracking method for human height mounted camera, e.g. the one attached near information or advertising stand. We use state-of-the-art particle filter approach and improve it by explicitly modeling of object visibility which makes the method able to cope with difficult object overlapping. We employ our own method based on online-boosting ...
Added: July 10, 2014
Ershov E., , in : 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW). : IEEE, 2022. P. 1287-1300.
This paper reviews the NTIRE 2022 challenge on night photography rendering. The challenge solicited solutions that processed RAW camera images captured in night scenes to produce a photo-finished output image encoded in the standard RGB (sRGB) space. Given the subjective nature of this task, the proposed solutions were evaluated based on the mean opinions of ...
Added: September 8, 2023
White M., Tarakanov A., Race C. et al., / arXiv. Series 2203.13718 "cs". 2022.
Finding efficient means of fingerprinting microstructural information is a critical step towards harnessing data-centric machine learning approaches. A statistical framework is systematically developed for compressed characterisation of a population of images, which includes some classical computer vision methods as special cases. The focus is on materials microstructure. The ultimate purpose is to rapidly fingerprint sample ...
Added: October 28, 2022
Arkhipova M., Экономика региона 2022 Т. 18 № 2 С. 581-594
The article examines new methodologies for modelling crop yield in agricultural regions of Russia based on the use of remote capabilities to get information on the field state. The proposed approach can be applied to develop indicator systems and create methodological platforms and models necessary to obtain more accurate estimates. In comparison with the traditional ...
Added: January 12, 2023
Kwon T., Li Y., Sawada T. et al., Vision Research 2016 Vol. 126 P. 264-277
This study, which was influenced a lot by Gestalt ideas, extends our prior work on the role of a priori constraints in the veridical perception of 3D shapes to the perception of 3D scenes. Our experiments tested how human sub-jects perceive the layout of a naturally-illuminated indoor scene that contains common symmetrical 3D objects standing ...
Added: September 15, 2015
Kirillov A., Gavrikov M., Lobacheva E. et al., , in : Proceedings of the 27th British Machine Vision Conference. : -, 2016. P. 1-12.
The Shape Boltzmann Machine (SBM) and its multilabel version MSBM have been recently introduced as deep generative models that capture the variations of an object shape. While being more flexible MSBM requires datasets with labeled parts of the objects for training. In the paper we present an algorithm for training MSBM using binary masks of ...
Added: February 24, 2017