26 Hits in 8.5 sec

Similarity-Aware Patchwork Assembly for Depth Image Super-resolution

Jing Li, Zhichao Lu, Gang Zeng, Rui Gan, Hongbin Zha
2014 2014 IEEE Conference on Computer Vision and Pattern Recognition  
This paper describes a patchwork assembly algorithm for depth image super-resolution.  ...  structures in the scene, and (5) the boundary coincidence between the resolution enhanced depth image and an optional aligned high resolution intensity image.  ...  Prior arts [23, 15] anisotropically diffuse depth values based on the boundaries shape on intensity image. We fuse the optional intensity image I by including it in the energy functional.  ... 
doi:10.1109/cvpr.2014.431 dblp:conf/cvpr/LiLZGZ14 fatcat:edrarlojj5eariz2v5fwtazedu

Depth map artifacts reduction: a review

Mostafa Ibrahim, Qiong Liu, Rizwan Khan, Jingyu Yang, Ehsan Adeli, You Yang
2020 IET Image Processing  
Depth maps are crucial for many visual applications, where they represent the positioning information of the objects in a three-dimensional scene.  ...  Usually, depth maps can be acquired via various devices, including Time of Flight, Kinect or light field camera, in practical applications.  ...  In [56] , anisotropic diffusion technique formulates inpainting task to fill the hole pixels in depth map aligned with colour image solving for a large sparse linear system.  ... 
doi:10.1049/iet-ipr.2019.1622 fatcat:fe5szwvvprdspptvsviw2e4dym

Image-guided ToF depth upsampling: a survey

Iván Eichhardt, Dmitry Chetverikov, Zsolt Jankó
2017 Machine Vision and Applications  
This has motivated many researchers to combine ToF cameras with other sensors in order to enhance and upsample depth images.  ...  In this paper, we review the approaches that couple ToF depth images with high-resolution optical images. Other classes of upsampling methods are also briefly discussed.  ...  Acknowledgements We are grateful to Zinemath Zrt for providing test data.  ... 
doi:10.1007/s00138-017-0831-9 fatcat:w2p3ebhysfarfk46phex753dxe

Color-Guided Depth Recovery From RGB-D Data Using an Adaptive Autoregressive Model

Jingyu Yang, Xinchen Ye, Kun Li, Chunping Hou, Yao Wang
2014 IEEE Transactions on Image Processing  
This paper proposes an adaptive color-guided autoregressive (AR) model for high quality depth recovery from low quality measurements captured by depth cameras.  ...  Being able to handle various types of depth degradations, the proposed method is versatile for mainstream depth sensors, time-of-flight camera, and Kinect, as demonstrated by experiments on real systems  ...  Park for providing recovered depth maps in [11] for comparison, and thank anonymous reviewers for their comments which help to significantly improve the paper.  ... 
doi:10.1109/tip.2014.2329776 pmid:24951695 fatcat:5lfcex5awncrdeybablcwaa5uq

Exploiting global priors for RGB-D saliency detection

Jianqiang Ren, Xiaojin Gong, Lu Yu, Wenhui Zhou, Michael Ying Yang
2015 2015 IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)  
To this end, we propose two priors, which are the normalized depth prior and the global-context surface orientation prior, and formulate them in the forms simple for computation.  ...  It first integrates the region contrast, together with the background, depth, and orientation priors to achieve a saliency map.  ...  Among them, the use of RGB-D images for salient object detection is attracting more and more interest, partially due to the advent of robust ranging sensors such as the Microsoft Kinect and Velodyne Lidars  ... 
doi:10.1109/cvprw.2015.7301391 dblp:conf/cvpr/RenGYZY15 fatcat:kpmgelrsnnelvkwpi7ai4rejoi

Explicit Edge Inconsistency Evaluation Model for Color-guided Depth Map Enhancement

Yifan Zuo, Qiang Wu, Jian Zhang, Ping An
2017 IEEE transactions on circuits and systems for video technology (Print)  
from the color image for depth enhancement leading to various defects such as texture-copy artifacts and blurring depth edges.  ...  Color-guided depth enhancement is to refine depth maps according to the assumption that the depth edges and the color edges at the corresponding locations are consistent.  ...  weights smooth pq   (IJBU), Spatial-depth super resolution for range images (JBUV) [9] , guided image filtering (Guided) [10] , edge-weighted NLM-regularization (NLMR) [4] , joint geodesic filtering  ... 
doi:10.1109/tcsvt.2016.2609438 fatcat:ij5p7dwvo5antjlyubl7kg52su

Computational Multi-View Imaging with Kinect

Xinchen Ye, Jingyu Yang, Hao Huang, Chunping Hou, Yao Wang
2014 IEEE transactions on broadcasting  
Index Terms-Multiview imaging, Kinect, depth restoration, matrix completion, view synthesis. Y. Wang is with the  ...  This paper proposes a lightweight multiview imaging approach with Kinect, a handheld integrated depth-color camera, under the depth-imagebased rendering framework.  ...  For low delay and low complexity, many methods focus on the enhancement of Kinect depth within the spatial domain.  ... 
doi:10.1109/tbc.2014.2345931 fatcat:pg6orbwmobbdbhu6xb2z5vajwu

Depth Image Upsampling based on Guided Filter with Low Gradient Minimization [article]

Hang Yang, Zhongbo Zhang
2018 arXiv   pre-print
In this paper, we present a novel upsampling framework to enhance the spatial resolution of the depth image.  ...  Since depth images have quite sparse gradients, it inspires us to regularize the gradients for improving depth upscaling results.  ...  [7] utilizes an anisotropic diffusion tensor to guide the depth map upsampling (TGV), the tensor is calculated from a HR intensity image. Aodha et al.  ... 
arXiv:1811.04620v1 fatcat:o66ts2de2vg4nmqi5cejms4aaq

Edge guided single depth image super resolution

Jun Xie, Rogerio Schmidt Feris, Ming-Ting Sun
2014 2014 IEEE International Conference on Image Processing (ICIP)  
In this paper, a novel framework for the single depth image superresolution is proposed.  ...  Index Terms-Single depth image, super resolution, edge-guided, joint bilateral up-sampling, Markov random field.  ...  In [23] , an anisotropic diffusion tensor, calculated from a high resolution intensity image, is used to guide the depth image upsampling (TGVL2).  ... 
doi:10.1109/icip.2014.7025766 dblp:conf/icip/XieFS14 fatcat:tsw2fdz2sra5hm7hsgi65prnz4

Edge-Guided Single Depth Image Super Resolution

Jun Xie, Rogerio Schmidt Feris, Ming-Ting Sun
2016 IEEE Transactions on Image Processing  
In this paper, a novel framework for the single depth image superresolution is proposed.  ...  Index Terms-Single depth image, super resolution, edge-guided, joint bilateral up-sampling, Markov random field.  ...  In [23] , an anisotropic diffusion tensor, calculated from a high resolution intensity image, is used to guide the depth image upsampling (TGVL2).  ... 
doi:10.1109/tip.2015.2501749 pmid:26599968 fatcat:xnxzwu7al5buxlps4v4y5br5iq

Deep Convolutional Grid Warping Network for Joint Depth Map Upsampling

Yoonmo Yang, Dongsin Kim, Byung Tae Oh
2020 IEEE Access  
The displacement vector for warping is obtained from an analysis of the corresponding high-resolution color image.  ...  Depth maps play an important role in the representation of 3D information.  ...  Liu and Gong proposed to use anisotropic heat diffusion filtering (ADF) [23] , where the known pixels of depth maps are set as heat sources, and depth enhancement is performed by diffusing depth value  ... 
doi:10.1109/access.2020.3015209 fatcat:s7minlrtuvcp7mqxu2sldetrgm

Literature Survey on Stereo Vision Disparity Map Algorithms

Rostam Affendi Hamzah, Haidi Ibrahim
2016 Journal of Sensors  
Generally, the main processing module for a software-based implementation uses only a central processing unit.  ...  To assist future researchers in developing their own stereo matching algorithms, a summary of the existing algorithms developed for every stage of processing is also provided.  ...  At each resolution, 35 iterations of the anisotropic diffusion process are performed.  ... 
doi:10.1155/2016/8742920 fatcat:o23jgt6w2bgnvegulnun5f6myi

Depth Map Upsampling via Multi-Modal Generative Adversarial Network

Daniel Tan, Jun-Ming Lin, Yu-Chi Lai, Joel Ilao, Kai-Lung Hua
2019 Sensors  
Our proposed model is trained on two different modalities, namely color images and depth maps.  ...  Autonomous robots for smart homes and smart cities mostly require depth perception in order to interact with their environments.  ...  Other learning-based methods like [27] phrased the depth map up-sampling task as a convex optimization problem with higher order regularization guided by anisotropic diffusion tensors extracted from  ... 
doi:10.3390/s19071587 fatcat:v3aw5etok5dpnp5lj6aqyxsohq

Multimedia super-resolution via deep learning: A survey

Khizar Hayat
2018 Digital signal processing (Print)  
We focus on the three important aspects of multimedia - namely image, video and multi-dimensions, especially depth maps.  ...  The recent phenomenal interest in convolutional neural networks (CNNs) must have made it inevitable for the super-resolution (SR) community to explore its potential.  ...  For details on Sentinel-1 to 5 and 5P visit 3) ATGV [177]: depth image upsampling guided by an anisotropic diffusion  ... 
doi:10.1016/j.dsp.2018.07.005 fatcat:bhzritty4fcvhay4v2iptj5kge

Scene Flow Estimation: A Survey [article]

Zike Yan, Xuezhi Xiang
2017 arXiv   pre-print
A future vision is illustrated with few questions arisen for discussion. This survey presents a general introduction and analysis of scene flow estimation.  ...  A total generalized variation regularization(TGV) [91] along with an anisotropic diffusion tensor was utilized to preserve edges.  ...  In addition, long range of distance may make the depth map transferred from disparity map unclear for visualization, which make image-based algorithm hard to work.  ... 
arXiv:1612.02590v3 fatcat:p5e64mpvqnflxmrrzjufqdourq
« Previous Showing results 1 — 15 out of 26 results