Filters








535 Hits in 10.9 sec

Cartographic Relief Shading with Neural Networks [article]

Bernhard Jenny, Magnus Heitzler, Dilpreet Singh, Marianna Farmakis-Serebryakova, Jeffery Chieh Liu, Lorenz Hurni
2020 arXiv   pre-print
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]

Dandan Ding, Zhan Ma, Di Chen, Qingshuang Chen, Zoe Liu, Fengqing Zhu
2021 arXiv   pre-print
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]

Zhiyong Wang, Jinxiang Chai, Shihong Xia
2018 arXiv   pre-print
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]

Dario Fuoli, Zhiwu Huang, Shuhang Gu, Radu Timofte, Arnau Raventos, Aryan Esfandiari, Salah Karout, Xuan Xu, Xin Li, Xin Xiong, Jinge Wang, Pablo Navarrete Michelini (+14 others)
2020 arXiv   pre-print
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]

Ke Li, Shichong Peng, Jitendra Malik
2018 arXiv   pre-print
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]

Mauricio Delbracio, Hossein Talebi, Peyman Milanfar
2021 arXiv   pre-print
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]

Kaicheng Liang, Xinyu Liu, Si Chen, Jun Xie, Wei Qing Lee, Linbo Liu, Hwee Kuan Lee
2020 arXiv   pre-print
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]

Andrey Ignatov, Nikolay Kobyshev, Radu Timofte, Kenneth Vanhoey, Luc Van Gool
2018 arXiv   pre-print
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

K. Suzanne Scherf, Daniel B. Elbich, Natalie V. Motta-Mena
2017 eNeuro  
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]

Thomas Köhler, Michel Bätz, Farzad Naderi, André Kaup, Andreas Maier, Christian Riess
2019 arXiv   pre-print
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]

Jay Whang, Mauricio Delbracio, Hossein Talebi, Chitwan Saharia, Alexandros G. Dimakis, Peyman Milanfar
2021 arXiv   pre-print
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

Andrey Ignatov, Nikolay Kobyshev, Radu Timofte, Kenneth Vanhoey, Luc Van Gool
2018 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)  
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]

Andreas Lugmayr, Martin Danelljan, Radu Timofte, Namhyuk Ahn, Dongwoon Bai, Jie Cai, Yun Cao, Junyang Chen, Kaihua Cheng, SeYoung Chun, Wei Deng, Mostafa El-Khamy (+34 others)
2020 arXiv   pre-print
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]

Fabian Mentzer, George Toderici, Michael Tschannen, Eirikur Agustsson
2020 arXiv   pre-print
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]

Younghyun Jo, Jaeyeon Kang, Seoung Wug Oh, Seonghyeon Nam, Peter Vajda, Seon Joo Kim
2020 arXiv   pre-print
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