28,186 Hits in 3.5 sec

Elements of style

Zhaoliang Lun, Evangelos Kalogerakis, Alla Sheffer
2015 ACM Transactions on Graphics  
To achieve this consistency we employ crowdsourcing to quantify the different components of our measure; we learn the relative perceptual importance of a range of elementary shape distances and other parameters  ...  Our measure is inspired by observations about style similarity in art history literature, which point to the presence of similarly shaped, salient, geometric elements as one of the key indicators of stylistic  ...  propose a style measure derived from and validated against a crowdsourced perceptual style similarity study.  ... 
doi:10.1145/2766929 fatcat:imj2srkcijelrai6i64smowuwu

Influence of musical elements on the perception of 'Chinese style' in music

Yu Zhang, Ziya Zhou, Maosong Sun
2022 Cognitive Computation and Systems  
In this study, a pipeline of performing a perceptual survey is designed to explore how different musical elements influence people's perception of 'Chinese style' in music.  ...  Previous musicological studies have explained how musical elements like melody and instruments shape a certain kind of music genre including Chinese music, but the findings cannot be directly applied to  ...  Zijin Li for providing valuable feedback during final drafting of the study.  ... 
doi:10.1049/ccs2.12036 fatcat:lgpr4iak7nacvdbqlmpa3efxxq

Feature-Style Encoder for Style-Based GAN Inversion [article]

Xu Yao, Alasdair Newson, Yann Gousseau, Pierre Hellier
2022 arXiv   pre-print
Our model achieves accurate inversion of real images from the latent space of a pre-trained style-based GAN model, obtaining better perceptual quality and lower reconstruction error than existing methods  ...  Our proposed method yields state-of-the-art results for style-based GAN inversion, significantly outperforming competing approaches.  ...  Our Feature-Style encoder, on the other hand, significantly improves the perceptual quality of the inversion and improves latent space editing; • We present a novel training approach, which learns two  ... 
arXiv:2202.02183v1 fatcat:7xtfszrk6vhgxavmz7zu2m2pfm

Psychological challenges for the analysis of style

2006 Artificial intelligence for engineering design, analysis and manufacturing  
This paper differentiates between a range of distinct meanings of 'style', and explores how designers and ordinary people learn and apply perceptual similarity classes and style concepts in different situations  ...  A range of psychological evidence indicates that style perception is dependent on knowledge, and involves the interaction of perceptual recognition of style features and explanatory inference processes  ...  Dr Kristina Lauche of the Technical University of Delft, and the nature of style with Calandra Eckert of Manor High School.  ... 
doi:10.1017/s089006040606015x fatcat:2w2qcpmcjbcbbmjwwwnr5onste

Parameter-Free Style Projection for Arbitrary Style Transfer [article]

Siyu Huang, Haoyi Xiong, Tianyang Wang, Bihan Wen, Qingzhong Wang, Zeyu Chen, Jun Huan, Dejing Dou
2022 arXiv   pre-print
In this task the feature-level content-style transformation plays a vital role for proper fusion of features.  ...  Existing feature transformation algorithms often suffer from loss of content or style details, non-natural stroke patterns, and unstable training.  ...  The learning objective of our style transfer model is composed of three parts, including the style loss, the content perceptual loss, and the content KL divergence loss.  ... 
arXiv:2003.07694v2 fatcat:pqhoa6ygvvddda5655at3jrvn4

Gran Stylissimo: The Audiovisual Elements and Styles in Computer and Video Games

Aki Järvinen
2002 Conference of the Digital Games Research Association  
Naming and analysing different styles and elements helps us to understand both what kind of audiovisual techniques persist and what has changed in the developing fi eld of computer and video games.  ...  In this paper the concept of audiovisual style is introduced to grasp these variations, and categorize existing games into three styles.  ...  Most buildings have elements such as windows, but their style (shape, size, ornamentation) can vary considerably. The whole architectonic style is a sum of all the individual elements.  ... 
dblp:conf/digra/Jarvinen02 fatcat:2cmlwnb6uzdvbhyqf5b3rbavhi

Functionality preserving shape style transfer

Zhaoliang Lun, Evangelos Kalogerakis, Rui Wang, Alla Sheffer
2016 ACM Transactions on Graphics  
Recent literature point to the presence of similarly shaped, salient geometric elements as a main indicator of stylistic similarity between 3D shapes.  ...  We use this metric to cast style transfer as a tabu search, which incrementally updates the target shape using compatible operations, progressively increasing its style similarity to the exemplar while  ...  Our algorithm's settings are learned from perceptual and geometric data and aim to achieve results that suit a typical user.  ... 
doi:10.1145/2980179.2980237 fatcat:7aeonziu6jeivmz4fdsljxjyci

Depth-aware neural style transfer

Xiao-Chang Liu, Ming-Ming Cheng, Yu-Kun Lai, Paul L. Rosin
2017 Proceedings of the Symposium on Non-Photorealistic Animation and Rendering - NPAR '17  
(a) style image, (b) content image, (c) result of [Johnson et al. 2016] and (d) our depthaware style transfer result.  ...  An e cient solution proposed by Johnson et al. trains feed-forward convolutional neural networks by de ning and optimizing perceptual loss functions.  ...  Deep Learning based Methods. With the development of both theory and hardware capability, deep learning o ers a novel alternative for style transfer.  ... 
doi:10.1145/3092919.3092924 dblp:conf/npar/LiuCLR17 fatcat:2w6tgrzhg5bkbopqafd3pn24z4

3DSNet: Unsupervised Shape-to-Shape 3D Style Transfer [article]

Mattia Segu, Margarita Grinvald, Roland Siegwart, Federico Tombari
2021 arXiv   pre-print
By sampling style codes from the learned distributions, we increase the variety of styles that our model can confer to an input shape.  ...  The proposed method can synthesize new 3D shapes both in the form of point clouds and meshes, combining the content and style of a source and target 3D model to generate a novel shape that resembles in  ...  A limited number of works investigated the shape style transfer problem in the pre-deep learning era, either relying on tabu search to iteratively update a sample to make it perceptually similar to the  ... 
arXiv:2011.13388v4 fatcat:lgiupah2kvg6hfgeik5fgb5gge

Style Permutation for Diversified Arbitrary Style Transfer

Pan Li, Dan Zhang, Lei Zhao, Duanqing Xu, Dongming Lu
2020 IEEE Access  
Compared with state-of-the-art diversified style transfer methods, our style permutation algorithm offers more flexibility.  ...  We propose a light-weighted yet efficient method named style permutation (SP) to tackle the limitation of the diversity without harming the original style information.  ...  We compute the L 1 norm of a vector in this paper. Besides, we use the Learned Perceptual Image Patch Similarity (LPIPS) metric proposed by [45] with their default settings.  ... 
doi:10.1109/access.2020.3034653 fatcat:lnfpa2zvovcj3p4gqylud2ijo4

Neural style transfer

Amir Semmo, Tobias Isenberg, Jürgen Döllner
2017 Proceedings of the Symposium on Non-Photorealistic Animation and Rendering - NPAR '17  
Input 'Mosaic' 'Udnie' 'La Muse' / Oil Paint 'The Scream' / Watercolor Neural Style Transfer Neural Style Transfer with Filtering This is the authors' version of the work.  ...  The de nitive version will be published in Proceedings of Non-Photorealistic Animation and Rendering (NPAR '17).  ...  This work was partly funded by the Federal Ministry of Education and Research (BMBF), Germany, for the AVA project 01IS15041B.  ... 
doi:10.1145/3092919.3092920 dblp:conf/npar/SemmoID17 fatcat:3udzwr4mcndozpawlr2q34b47i

Perceptual-motor styles

Pierre-Paul Vidal, Francesco Lacquaniti
2021 Experimental Brain Research  
of the term perceptual-motor style in neurosciences.  ...  Here, we cover some potential applications of the concept of perceptual-motor style to different areas of neuroscience, both in the healthy and the diseased.  ...  On the other hand, numerous studies also show that the perceptual-motor style can evolve with proactive learning.  ... 
doi:10.1007/s00221-021-06049-0 pmid:33675378 pmcid:PMC8144157 fatcat:oc5laykc3rc33l6nwgtfjwwodm

3D Material Style Transfer

Chuong H. Nguyen, Tobias Ritschel, Karol Myszkowski, Elmar Eisemann, Hans-Peter Seidel
2012 Computer graphics forum (Print)  
were assigned to similar materials.  ...  It formulates the problem as a combinatorial optimization of assigning discrete materials extracted from the guide source to discrete objects in the target 3D scene.  ...  To compute the difference between two shapes we employ a 2D Angular Radial Transform (ART) [Bob01] , and use the corresponding shape descriptor vector composed of 35 elements.  ... 
doi:10.1111/j.1467-8659.2012.03022.x fatcat:xycmu3e3z5cc7c7xai4dazalvq

Learning Typographic Style [article]

Shumeet Baluja
2016 arXiv   pre-print
Thousands of different font-faces have been created with enormous variations in the characters. In this paper, we learn the style of a font by analyzing a small subset of only four letters.  ...  of the approach.  ...  Recently, growing attention has been devoted to style, not only in terms of fonts [8, 9, 10] , but in perceptual shape similarity for architecture and rigid objects [11] , computer graphics [12] , cursive  ... 
arXiv:1603.04000v1 fatcat:lfzzngc5wrbg7hds5n7lr7lyee

Typography With Decor: Intelligent Text Style Transfer

Wenjing Wang, Jiaying Liu, Shuai Yang, Zongming Guo
2019 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)  
Decorative elements pose a challenge to spontaneously handle basal text effects and decor, which are two different styles.  ...  A novel text effect transfer network is proposed to infer the styled version of the target text.  ...  Notice that insignificant elements usually share a similar shape with other elements, while significant elements often have a unique shape.  ... 
doi:10.1109/cvpr.2019.00604 dblp:conf/cvpr/Wang00G19 fatcat:das5erssqjgczmoccklpylfqce
« Previous Showing results 1 — 15 out of 28,186 results