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
Cartographic Relief Shading with Neural Networks
[article]
2020
arXiv
pre-print
Preserved Fulltext
We replicate hand-drawn relief shading using U-Net neural networks. ...
Shaded relief is an effective method for visualising terrain on topographic maps, especially when the direction of illumination is adapted locally to emphasise individual terrain features. ...
We also thank the following experts for participating in the evaluation: Jürg Gilgen, Thomas ...
arXiv:2010.01256v1
fatcat:3dda2d6d5bgtph6zjktoumbo7u
Advances In Video Compression System Using Deep Neural Network: A Review And Case Studies
[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.
On post-processing, we demonstrate two neural adaptive filters to respectively facilitate the in-loop and post filtering for the enhancement of compressed frames. ...
On pre-processing, we show a switchable texture-based video coding example that leverages DNN-based scene understanding to extract semantic areas for the improvement of subsequent video coder. ...
For "perceptually insignificant" regions, users will not perceive compression or processing impairments without a side-by-side comparison with the original sample. ...
arXiv:2101.06341v1
fatcat:63vikavtpnb3dilixbakkcbwnq
Combining Recurrent Neural Networks and Adversarial Training for Human Motion Synthesis and Control
[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.
Our key idea is to combine recurrent neural networks (RNNs) and adversarial training for human motion modeling. ...
This paper introduces a new generative deep learning network for human motion synthesis and control. ...
The accompanying video shows a side-by-side comparison of generated motions from RNNs with and without adversarial training. ...
arXiv:1806.08666v1
fatcat:hfgokt7nqfee7d3nry7vvuhtai
AIM 2020 Challenge on Video Extreme Super-Resolution: Methods and Results
[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.
Common scaling factors for learned video super-resolution (VSR) do not go beyond factor 4. ...
Track 2 therefore aims at generating visually pleasing results, which are ranked according to human perception, evaluated by a user study. ...
Again, we generated side-by-side videos between all methods for comparison in a one vs. one setting. ...
arXiv:2009.06290v1
fatcat:bbgfzmwupfgcnigwr2onun4zzm
Super-Resolution via Conditional Implicit Maximum Likelihood Estimation
[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.
Single-image super-resolution (SISR) is a canonical problem with diverse applications. ...
We demonstrate greater effectiveness at noise reduction and preservation of the original colours and shapes, yielding more realistic super-resolved images. ...
CONCLUSION In this paper, we proposed a new method for super-resolution, known as Super-Resolution Implicit Model (SRIM), based on the recent proposed method of Implicit Maximum Likelihood Estimation ( ...
arXiv:1810.01406v1
fatcat:5ew3exgylja55jfnuidgnpxzbu
Projected Distribution Loss for Image Enhancement
[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.
Other Versions
on reference-based perceptual losses. ...
More explicitly, we show that in imaging applications such as denoising, super-resolution, demosaicing, deblurring and JPEG artifact removal, the proposed learning loss outperforms the current state-of-the-art ...
Average pairwise human preference for single image 4x super-resolution. Each value represents the fraction of times the Amazon Mechanical Turk raters chose the row over the column. ...
arXiv:2012.09289v2
fatcat:5osphoyk6bghvg5ljyzrcdd4em
Resolution enhancement and realistic speckle recovery with generative adversarial modeling of micro-optical coherence tomography
[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
GANs have been previously used for resolution enhancement of photography and optical microscopy images. We have adapted and improved this technique for OCT image generation. ...
Accuracy of resolution enhancement compared to ground truth was quantified with human perceptual accuracy tests performed by an OCT expert. ...
Chen-Hsin Sun for helpful conversations on ophthalmic OCT.
Disclosures The authors declare no conflicts of interest. ...
arXiv:2003.06035v2
fatcat:jbrx5ldk3bbdrkv5dswt5izrvi
WESPE: Weakly Supervised Photo Enhancer for Digital Cameras
[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
Besides standard objective metrics and subjective user study, we train a virtual rater in the form of a separate CNN that mimics human raters on Flickr data and use this network to get reference scores ...
Hence, our solution is repeatable for any camera: collecting the data and training can be achieved in a couple of hours. In this work, we emphasize on extensive evaluation of obtained results. ...
The user’s task was to choose the preferred picture
benefits less from the WESPE image healing. Moreover, tar- among two displayed side by side. ...
arXiv:1709.01118v2
fatcat:bt6t7lqbpbaixo53okrfdxnrqa
Investigating the Influence of Biological Sex on the Behavioral and Neural Basis of Face Recognition
2017
eNeuro
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 2019; you can also visit the original URL.
The file type is application/pdf.
Face recognition is an essential skill for navigating human social interactions, which is reflected equally in the behavior and neural architecture of men and women. ...
There were no sex differences in the magnitude of the neural responses in any face-processing region. Furthermore, there was no OGB in the neural responses of either the male or female participants. ...
An adult male face and an adult female face were presented side-by-side and labeled as "John" and "Jane." Participants were given 10 seconds to encode the faces. ...
doi:10.1523/eneuro.0104-17.2017
pmid:28497111
pmcid:PMC5423736
fatcat:h3roi2ysezhjtkjfdo2tih7znm
Toward Bridging the Simulated-to-Real Gap: Benchmarking Super-Resolution on Real Data
[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.
Note that this fulltext copy is not of the "primary" version of this work. The version it corresponds to is:
2018 pre-print arXiv:1809.06420v1 fatcat:vvquobk6e5hjridqjbwb6mr6fq
Capturing ground truth data to benchmark super-resolution (SR) is challenging. ...
Toward bridging this simulated-to-real gap, we introduce the Super-Resolution Erlangen (SupER) database, the first comprehensive laboratory SR database of all-real acquisitions with pixel-wise ground truth ...
ACKNOWLEDGMENTS We would like to thank all users of our human subject study for their participation. We also thank the authors of prior works for providing the source codes for our benchmark. ...
arXiv:1809.06420v2
fatcat:sskqa6dbevddhjhghsffnikcoy
Deblurring via Stochastic Refinement
[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 2022; you can also visit the original URL.
The file type is application/pdf.
Other Versions
Our predict-and-refine approach also enables much more efficient sampling compared to typical diffusion models. ...
These metrics are known to be poorly correlated with human perception, and often lead to unrealistic reconstructions. ...
Average pairwise human preference for deblurring results
We also evaluate our GoPro-trained model on the HIDE on the GoPro dataset [50]. ...
arXiv:2112.02475v2
fatcat:hi5fbbjuijhwnlq624bhrqfkiu
WESPE: Weakly Supervised Photo Enhancer for Digital Cameras
2018
2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)
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.
Besides standard objective metrics and subjective user study, we train a virtual rater in the form of a separate CNN that mimics human raters on Flickr data and use this network to get reference scores ...
Hence, our solution is repeatable for any camera: collecting the data and training can be achieved in a couple of hours. In this work, we emphasize on extensive evaluation of obtained results. ...
The user's task was to choose the preferred picture among two displayed side by side. ...
doi:10.1109/cvprw.2018.00112
dblp:conf/cvpr/IgnatovKTVG18
fatcat:ovlvgdopwbba3m5s5sahr5xhni
NTIRE 2020 Challenge on Real-World Image Super-Resolution: Methods and Results
[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.
In both tracks, the ultimate goal is to achieve the best perceptual quality, evaluated using a human study. ...
This paper reviews the NTIRE 2020 challenge on real world super-resolution. It focuses on the participating methods and final results. ...
The test candidates were shown a side-by-side comparison of a sample prediction of a certain method and the corresponding reference ground-truth. ...
arXiv:2005.01996v1
fatcat:ewngd7chdve3fbvwis32v64ruq
High-Fidelity Generative Image Compression
[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
The study shows that our method is preferred to previous approaches even if they use more than 2x the bitrate. ...
We bridge the gap between rate-distortion-perception theory and practice by evaluating our approach both quantitatively with various perceptual metrics, and with a user study. ...
Acknowledgments The authors would like to thank Johannes Balle, Sergi Caelles, Sander Dielmann, and David Minnen for the insightful discussions and feedback. ...
arXiv:2006.09965v3
fatcat:i7d6cpbeobfidf4jwqo2rt5fcm
Learning the Loss Functions in a Discriminative Space for Video Restoration
[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.
Meanwhile, the loss functions for optimizing deep neural networks remain relatively unchanged. ...
To this end, we propose a new framework for building effective loss functions by learning a discriminative space specific to a video restoration task. ...
For EDVR comparison, we randomly show two videos side by side, and ask the users to choose more pleasing one. The comparison is performed 30 times for each scene. ...
arXiv:2003.09124v1
fatcat:2b53t4cawrb5pb622qqkyddrri
« Previous
Showing results 1 — 15 out of 535 results