Results 241 to 250 of about 4,496,548 (308)
Some of the next articles are maybe not open access.
Multi-Scale Frequency Reconstruction for Guided Depth Map Super-Resolution via Deep Residual Network
IEEE transactions on circuits and systems for video technology (Print), 2020The depth maps obtained by the consumer-level sensors are always noisy in the low-resolution (LR) domain. Existing methods for the guided depth super-resolution, which are based on the pre-defined local and global models, perform well in general cases (e.
Y. Zuo +5 more
semanticscholar +1 more source
Depth cube display using depth map
SPIE Proceedings, 2011We propose Depth Cube Display (DCD) method using depth map. The structure of the proposed method consists of two parts: A projection part composed of projector for generating image and a Twisted Nematic Liquid Crystal display (TNLCD) as polarization modulating device for adjusting the proper depth and a display part composed of air-spaced stack of ...
Jung, Jung-Hun +2 more
openaire +1 more source
Monocular Depth Estimation Using Relative Depth Maps
2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2019We propose a novel algorithm for monocular depth estimation using relative depth maps. First, using a convolutional neural network, we estimate relative depths between pairs of regions, as well as ordinary depths, at various scales. Second, we restore relative depth maps from selectively estimated data based on the rank-1 property of pairwise ...
Jae-Han Lee, Chang-Su Kim
openaire +1 more source
Depth-map completion for large indoor scene reconstruction
Pattern Recognition, 2020Traditional Multi View Stereo (MVS) algorithms are often difficult to deal with large-scale indoor scene reconstruction, due to the photo-consistency measurement errors in weak textured regions, which are commonly exist in indoor scenes.
Hongmin Liu, Xincheng Tang, Shuhan Shen
semanticscholar +1 more source
IEEE transactions on circuits and systems for video technology (Print), 2020
3D high-efficiency video coding (3D-HEVC) is the latest standard for 3D video compression created by the ISO/IEC MPEG and ITU-T Video Coding Experts Group (VCEG) based on a new video format called multiview texture videos plus depth maps (MVDs).
Hamza Hamout, Abderrahmane Elyousfi
semanticscholar +1 more source
3D high-efficiency video coding (3D-HEVC) is the latest standard for 3D video compression created by the ISO/IEC MPEG and ITU-T Video Coding Experts Group (VCEG) based on a new video format called multiview texture videos plus depth maps (MVDs).
Hamza Hamout, Abderrahmane Elyousfi
semanticscholar +1 more source
Region-based depth recovery for highly sparse depth maps
2017 IEEE International Conference on Image Processing (ICIP), 2017The accurate recovery of missing values in depth maps is an important problem in computer vision and image processing. In depth maps with large, irregular missing regions (i.e., sparse depth maps) inaccuracies arise when depth values of known pixels are used to recover depth near object edges and depth discontinuities (leakage).
Kämäräinen Joni, Pertuz Said
openaire +1 more source
Hierarchical Features Driven Residual Learning for Depth Map Super-Resolution
IEEE Transactions on Image Processing, 2019Rapid development of affordable and portable consumer depth cameras facilitates the use of depth information in many computer vision tasks such as intelligent vehicles and 3D reconstruction.
Chunle Guo +5 more
semanticscholar +1 more source
Proceedings. 17th Brazilian Symposium on Computer Graphics and Image Processing, 2004
Traditional shadow maps store a single depth value per cell, leading to a binary outcome by the shadow test (either lit or in shadow), and are prone to produce aliased shadow borders. We present a new approach that produces better estimates of shadow percentages and, in combination with percentage closer filtering (PCF), reduces aliasing artifacts ...
C.A. Pagot +2 more
openaire +1 more source
Traditional shadow maps store a single depth value per cell, leading to a binary outcome by the shadow test (either lit or in shadow), and are prone to produce aliased shadow borders. We present a new approach that produces better estimates of shadow percentages and, in combination with percentage closer filtering (PCF), reduces aliasing artifacts ...
C.A. Pagot +2 more
openaire +1 more source
bams, 2013
Abstract A human observer is able to determine the color of objects independent of the light illuminating these objects. This ability is known as color constancy. In the first stages of visual information processing, data are analyzed with respect to wavelength composition, orientation, motion, and depth.
Marc Ebner, Johannes Hansen
openaire +1 more source
Abstract A human observer is able to determine the color of objects independent of the light illuminating these objects. This ability is known as color constancy. In the first stages of visual information processing, data are analyzed with respect to wavelength composition, orientation, motion, and depth.
Marc Ebner, Johannes Hansen
openaire +1 more source
Multi-Direction Dictionary Learning Based Depth Map Super-Resolution With Autoregressive Modeling
IEEE transactions on multimedia, 20203D depth cameras have become more and more popular in recent years. However, depth maps captured by these cameras can hardly be used in 3D reconstruction directly because they often suffer from low resolution and blurring depth discontinuities.
Jin Wang +5 more
semanticscholar +1 more source