A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
Filters
Multi-Domain Image Completion for Random Missing Input Data
[article]
2020
arXiv
pre-print
Preserved Fulltext
To tackle this problem, we propose a general approach to complete the random missing domain(s) data in real applications. ...
We further illustrate that the learned representation in multi-domain image completion could be leveraged for high-level tasks, e.g., segmentation, by introducing a unified framework consisting of image ...
The goal of our first task is to complete all the missing domains for a random input sample. ...
arXiv:2007.05534v1
fatcat:buih5jhb5javlla4mmz7v32eqm
VIGAN: Missing view imputation with generative adversarial networks
2017
2017 IEEE International Conference on Big Data (Big Data)
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
The missing data problem has been challenging to address in multi-view data analysis. Especially, when certain samples miss an entire view of data, it creates the missing view problem. ...
This approach first treats each view as a separate domain and identifies domain-to-domain mappings via a GAN using randomly-sampled data from each view, and then employs a multi-modal denoising autoencoder ...
The authors would like to thank Xia Xiao for helpful discussion, and Xinyu Wang for helping with the experiments. ...
doi:10.1109/bigdata.2017.8257992
pmid:29457155
pmcid:PMC5813842
dblp:conf/bigdataconf/ShangPSCLB17
fatcat:6ag5w43xunaq3hhcb3szbfxgu4
VIGAN: Missing View Imputation with Generative Adversarial Networks
[article]
2017
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
Other Versions
The missing data problem has been challenging to address in multi-view data analysis. Especially, when certain samples miss an entire view of data, it creates the missing view problem. ...
This approach first treats each view as a separate domain and identifies domain-to-domain mappings via a GAN using randomly-sampled data from each view, and then employs a multi-modal denoising autoencoder ...
The authors would like to thank Xia Xiao for helpful discussion, and Xinyu Wang for helping with the experiments. ...
arXiv:1708.06724v5
fatcat:kpemkzh7mffshf3t646ixngqpy
CollaGAN : Collaborative GAN for Missing Image Data Imputation
[article]
2019
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
Other Versions
CollaGAN converts an image imputation problem to a multi-domain images-to-image translation task so that a single generator and discriminator network can successfully estimate the missing data using the ...
Although many techniques have been developed for imputing missing data, the image imputation is still difficult due to complicated nature of natural images. ...
Once all missing values have been imputed, the data set can be used as an input for standard techniques designed for the complete data set. ...
arXiv:1901.09764v3
fatcat:ywhskg32jvb6jf4kqlktixskiq
Multivariate Time Series as Images: Imputation Using Convolutional Denoising Autoencoder
2020
International Symposium on Intelligent Data Analysis
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
All our experiments were performed on 5 UEA MTSC multivariate time series datasets, where 20 to 50% of the data was simulated to be missing completely at random. ...
Missing data is a common occurrence in the time series domain, for instance due to faulty sensors, server downtime or patients not attending their scheduled appointments. ...
The first one is Missing Completely At Random (MCAR), where the missingness of the data does not depend on itself or any other variables. ...
doi:10.1007/978-3-030-44584-3_1
dblp:conf/ida/SafiBUS20
fatcat:ohmm3kxiyzgwth7od2t6grlvp4
Adversarial Open Domain Adaptation for Sketch-to-Photo Synthesis
[article]
2021
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2021; you can also visit the original URL.
The file type is application/pdf.
Note that this fulltext copy is not of the "primary" version of this work. The version it corresponds to is:
2021 pre-print arXiv:2104.05703v1 fatcat:cggnoz744zf3bpq4lmlcor3xwi
in the training data. ...
Our method takes advantage of the learned sketch-to-photo and photo-to-sketch mapping of in-domain data and generalizes it to the open-domain classes. ...
However, if we directly train the multi-class generator with the loss defined in Equation 4, the training objectives for open-domain classes M become the following form due to the missing sketches s: L ...
arXiv:2104.05703v2
fatcat:m4kkb6kje5botkae4xe25pxdu4
Robust Image Completion via Deep Feature Transformations
2019
IEEE Access
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2021; you can also visit the original URL.
The file type is application/pdf.
For many practical applications, it is essential to address both geometric corrections and missing information reconstruction of face images and natural images. ...
In this paper, we propose a novel robust missing information reconstruction framework via deep feature transformations to simultaneously address both geometric corrections and image completion. ...
The key characteristics of our deep feature transformer network is to process the input data in deep feature domain by: (i) extracting deep multi-channel feature maps to exploit the advantage that feature ...
doi:10.1109/access.2019.2935130
fatcat:be3w77l6sres3iebeqguxri2fa
Domain Embedded Multi-model Generative Adversarial Networks for Image-based Face Inpainting
[article]
2020
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
Other Versions
To solve this problem, we present a domain embedded multi-model generative adversarial model for inpainting of face images with large cropped regions. ...
However, traditional face inpainting methods mainly focus on the generated image resolution of the missing portion without consideration of the special particularities of the human face explicitly and ...
CONCLUSION We proposed a Domain Embedded Multi-model Generative Adversarial Network for face image inpainting. ...
arXiv:2002.02909v2
fatcat:kxx3tzmwybeu7p6u4ofuctjwq4
Unified Multi-Domain Learning and Data Imputation using Adversarial Autoencoder
[article]
2020
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
We present a novel framework that can combine multi-domain learning (MDL), data imputation (DI) and multi-task learning (MTL) to improve performance for classification and regression tasks in different ...
and correctly perform data imputation on missing data. ...
This creates a missing completely at random (MCAR) case, where there is no dependency on any of the variables. ...
arXiv:2003.07779v1
fatcat:ptuep5jeurawrd6ecz3mw2jbwa
Improving Missing Data Imputation with Deep Generative Models
[article]
2019
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
Previous experiments with Generative Adversarial Networks and Variational Autoencoders showed interesting results in this domain, but it is not clear which method is preferable for different use cases. ...
The goal of this work is twofold: we present a comparison between missing data imputation solutions based on deep generative models, and we propose improvements over those methodologies. ...
Values are considered to be missing completely at random (MCAR) when the probability that they are missing is independent both on the value and on other observable values of the data. ...
arXiv:1902.10666v1
fatcat:lw2cljif3fccxlidp6g5q3etky
Filling the Gaps: Predicting Missing Joints of Human Poses Using Denoising Autoencoders
[chapter]
2019
Landolt-Börnstein - Group III Condensed Matter
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
In this work, we propose a method for predicting the missing joints from incomplete human poses. ...
of the low dimensional domain. ...
This behavior is acceptable when input data represents classes (e.g. images of numbers or letters). ...
doi:10.1007/978-3-030-11012-3_29
fatcat:aafp532sxnaglhc2hn5gz6vw3a
Which Contrast Does Matter? Towards a Deep Understanding of MR Contrast using Collaborative GAN
[article]
2019
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
These approaches are potentially important for image imputation problems, where complete set of data is often difficult to obtain and image synthesis is one of the key solutions for handling the missing ...
data problem. ...
Once all missing data have been imputed, the dataset can be used as an input for standard techniques designed for the complete dataset. ...
arXiv:1905.04105v1
fatcat:tcldznehefeojp7tkc7ipld6f4
FaceShop: Deep Sketch-based Face Image Editing
[article]
2018
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
Other Versions
Our system is based on a novel sketch domain and a convolutional neural network trained end-to-end to automatically learn to render image regions corresponding to the input strokes. ...
To achieve high quality and semantically consistent results we train our neural network on two simultaneous tasks, namely image completion and image translation. ...
However, their system can only complete missing eye regions. In our sketch-based image editing system we also leverage a GAN loss to train CNNs for image completion. ...
arXiv:1804.08972v2
fatcat:jvi2hqxq3jh5lkrxu4f5tbnkty
Depth Completion with RGB Prior
[article]
2020
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
The data was collected with low-end depth cameras and the ground truth depth was generated by multi-view fusion. ...
Here, we developed a deep model to correct the depth channel in RGBD images, aiming to restore the depth information to the required accuracy. ...
We conclude with dense depth completion, where the depth data is dense but has missing or erroneous regions. ...
arXiv:2008.07861v1
fatcat:jkptc5ytxzdzjl76i6sidgodm4
Multi-Modal Masked Pre-Training for Monocular Panoramic Depth Completion
[article]
2022
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2022; you can also visit the original URL.
The file type is application/pdf.
Note that this fulltext copy is not of the "primary" version of this work. The version it corresponds to is:
2022 pre-print arXiv:2203.09855v2 fatcat:es2k72putvbuvkw4durzhaobmqOther Versions
To deal with the PDC task, we train a deep network that takes both depth and image as inputs for the dense panoramic depth recovery. ...
In this paper, we formulate a potentially valuable panoramic depth completion (PDC) task as panoramic 3D cameras often produce 360 depth with missing data in complex scenes. ...
Different from MAE where masking is performed on single RGB data, we propose to mask both RGB image and sparse depth with the shared random mask to produce incomplete RGB-D pair as input for pre-training ...
arXiv:2203.09855v3
fatcat:22ezqeuxhjgtneppgwcblhqhbi
« Previous
Showing results 1 — 15 out of 61,869 results