Neural style transfer

Semmo, Amir; Isenberg, Tobias; Döllner, Jürgen

doi:10.1145/3092919.3092920

Cited by 42 publications

(5 citation statements)

References 85 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Combinations of techniques also merit consideration, such as using edge enhancement from FlowAbs with other techniques, or combining color manipulation with spatial filters. As future work, we also plan to investigate how neural style transfer [Gatys et al 2016;Johnson et al 2016;Semmo et al 2017] can be used to replicate illustrations found in medical textbooks. Such techniques can be quite promising in our context, although their outcome is still hard to control.…”

Section: Limitationsmentioning

confidence: 99%

Reducing affective responses to surgical images through color manipulation and stylization

Besançon

Semmo

Biau

et al. 2018

Proceedings of the Joint Symposium on Computational Aesthetics and Sketch-Based Interfaces and Modeling and Non-Photorealistic

Self Cite

View full text Add to dashboard Cite

Original photo of a lasagna dish.Output of HueShift2. Output of FlowAbs [Kyprianidis and Döllner 2008].Figure 1: Two techniques studied in this article, each using a different strategy for making surgery images easier to look at. ABSTRACTWe present the first empirical study on using color manipulation and stylization to make surgery images more palatable. While aversion to such images is natural, it limits many people's ability to satisfy their curiosity, educate themselves, and make informed decisions. We selected a diverse set of image processing techniques, and tested them both on surgeons and lay people. While many artistic methods were found unusable by surgeons, edge-preserving image smoothing gave good results both in terms of preserving information (as judged by surgeons) and reducing repulsiveness (as judged by lay people). Color manipulation turned out to be not as effective. CCS CONCEPTS• Computing methodologies → Non-photorealistic rendering; Image processing; • Human-centered computing → Empirical studies in HCI ; * Lonni Besançon is also with Linköping University, Sweden.Publication rights licensed to ACM. ACM acknowledges that this contribution was authored or co-authored by an employee, contractor or affiliate of a national government. As such, the Government retains a nonexclusive, royalty-free right to publish or reproduce this article, or to allow others to do so, for Government purposes only.

show abstract

Section: Limitationsmentioning

confidence: 99%

Reducing affective responses to surgical images through color manipulation and stylization

Besançon

Semmo

Biau

et al. 2018

Proceedings of the Joint Symposium on Computational Aesthetics and Sketch-Based Interfaces and Modeling and Non-Photorealistic

Self Cite

View full text Add to dashboard Cite

show abstract

“…At the opposite end of the interaction spectrum, most generic example-based methods (e.g., [Bénard et al 2013;Fišer et al 2016]) lack intuitive local control of the style transfer, as discussed by Semmo et al [2017]. Only a few methods targeting a specific task or style, such as hatching illustration [Gerl and Isenberg 2013], offer tools that let the user guide the underlying synthesis algorithm.…”

Section: Related Workmentioning

confidence: 99%

MNPR

Montesdeoca

Seah

Semmo

et al. 2018

Proceedings of the Joint Symposium on Computational Aesthetics and Sketch-Based Interfaces and Modeling and Non-Photorealistic

Self Cite

View full text Add to dashboard Cite

show abstract

“…However, it was not until the late 20 th century that computers were used to simulate paintings [Hae90]. In the course of following decades, the field of artistic stylization [KCWI13] has significantly developed and extended by learning‐based methods, such as Neural Style Transfers (NSTs) [SID17, JYF * 20]. Even though a large number of image stylization techniques exist, extending these to video remains challenging.…”

Section: Introductionmentioning

confidence: 99%

Interactive Control over Temporal Consistency while Stylizing Video Streams

Shekhar

Reimann

Hilscher

et al. 2023

Computer Graphics Forum

Self Cite

View full text Add to dashboard Cite

Image stylization has seen significant advancement and widespread interest over the years, leading to the development of a multitude of techniques. Extending these stylization techniques, such as Neural Style Transfer (NST), to videos is often achieved by applying them on a per‐frame basis. However, per‐frame stylization usually lacks temporal consistency, expressed by undesirable flickering artifacts. Most of the existing approaches for enforcing temporal consistency suffer from one or more of the following drawbacks: They (1) are only suitable for a limited range of techniques, (2) do not support online processing as they require the complete video as input, (3) cannot provide consistency for the task of stylization, or (4) do not provide interactive consistency control. Domain‐agnostic techniques for temporal consistency aim to eradicate flickering completely but typically disregard aesthetic aspects. For stylization tasks, however, consistency control is an essential requirement as a certain amount of flickering adds to the artistic look and feel. Moreover, making this control interactive is paramount from a usability perspective. To achieve the above requirements, we propose an approach that stylizes video streams in real‐time at full HD resolutions while providing interactive consistency control. We develop a lite optical‐flow network that operates at 80 Frames per second (FPS) on desktop systems with sufficient accuracy. Further, we employ an adaptive combination of local and global consistency features and enable interactive selection between them. Objective and subjective evaluations demonstrate that our method is superior to state‐of‐the‐art video consistency approaches. maxreimann.github.io/stream‐consistency

show abstract

Neural style transfer

Cited by 42 publications

References 85 publications

Reducing affective responses to surgical images through color manipulation and stylization

Reducing affective responses to surgical images through color manipulation and stylization

MNPR

Interactive Control over Temporal Consistency while Stylizing Video Streams

Contact Info

Product

Resources

About