StyleProp: Real‐time Example‐based Stylization of 3D Models

Hauptfleisch, Filip; Texler, Ondřej; Texler, Aneta; Křivánek, Jaroslav; Sýkora, Daniel

doi:10.1111/cgf.14169

Cited by 12 publications

(3 citation statements)

References 56 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Therefore, most buttons are intuitive and touch-based. In Figure 4, we can see the application's QR code scanning interface, the reconstruction model 360° viewing interface, the hand-drawn image selection interface, and the face style transformation interface [15][16][17][18].…”

Section: User Interfacementioning

confidence: 99%

Art Museum Experience Application: Promoting Visitor Exploration of Mask Artifacts Through Stylization

Jin,

Zhang,

Hua

et al. 2024

Frontiers in Artificial Intelligence and Applications

View full text Add to dashboard Cite

This paper introduces a mask face style transformation method based on a mobile application, bringing a new experience to museum visits. The application is able to personalize the style of faces in photos or videos taken by visitors, integrating with original digital hand-drawn images created by designers. This interaction allows visitors to engage closely with the mask artifacts in the museum, thereby gaining a deeper understanding of the cultural background and historical information. To enhance the real-time and immersive feature matching between faces and mask images, various existing works were explored and analyzed. Drawing from the latest research findings, we discussed the connections between mask artifacts, mobile application, and faces. The results indicate that the mask face-changing application can enrich visitors’ experience, demonstrating the effectiveness and potential of the application in enhancing museum visiting experiences.

show abstract

Section: User Interfacementioning

confidence: 99%

Art Museum Experience Application: Promoting Visitor Exploration of Mask Artifacts Through Stylization

Jin,

Zhang,

Hua

et al. 2024

Frontiers in Artificial Intelligence and Applications

View full text Add to dashboard Cite

show abstract

“…Most approaches focus either on stylizing a single object, using either meshes [Ma et al 2014] or point clouds [Segu et al 2020], or material [Nguyen et al 2012]. Later work focuses on performing style transfer on both geometry and texture [Hauptfleisch et al 2020;Kato et al 2018;Yin et al 2021], but still limited to single objects.…”

Section: D Style Transfermentioning

confidence: 99%

SNeRF: Stylized Neural Implicit Representations for 3D Scenes

Nguyen-Phuoc¹,

Liu²,

Liu³

2022

Preprint

View full text Add to dashboard Cite

Fig. 1. Given a neural implicit scene representation trained with multiple views of a scene, SNeRF stylizes the 3D scene to match a reference style. SNeRF works with a variety of scene types (indoor, outdoor, 4D dynamic avatar) and generates novel views with cross-view consistency.This paper presents a stylized novel view synthesis method. Applying stateof-the-art stylization methods to novel views frame by frame often causes jittering artifacts due to the lack of cross-view consistency. Therefore, this paper investigates 3D scene stylization that provides a strong inductive bias for consistent novel view synthesis. Specifically, we adopt the emerging neural radiance fields (NeRF) as our choice of 3D scene representation for their capability to render high-quality novel views for a variety of scenes. However, as rendering a novel view from a NeRF requires a large number of samples, training a stylized NeRF requires a large amount of GPU memory that goes beyond an off-the-shelf GPU capacity. We introduce a new training method to address this problem by alternating the NeRF and stylization optimization steps. Such a method enables us to make full use of our hardware memory capacity to both generate images at higher resolution and adopt more expressive image style transfer methods. Our experiments show that our method produces stylized NeRFs for a wide range of content, including indoor, outdoor and dynamic scenes, and synthesizes high-quality novel views with cross-view consistency.

show abstract

“…Using a computer to synthesize an ink image with Chinese cultural characteristics [3] and integrating traditional art forms into computer technology-related applications can not only expand the scope of computer applications, but also promote the development of national culture. Hauptfleisch et al (2020) [4] proposed a new method to achieve real-time non-photorealistic rendering of a three-dimensional (3D) model, where the hand-drawn example specifies its appearance. The synthesis based on the guide patch is used to obtain high visual quality and time consistency.…”

Section: Introductionmentioning

confidence: 99%

Deep Learning in Computer Real-time Graphics and Image Using the Visual Effects of Non-photorealistic Rendering of Ink Painting

2022

FAR

View full text Add to dashboard Cite

This study is to explore the effect of deep learning algorithms applied to the non-photorealistic rendering (NPR) of ink painting. The powerful processing capabilities of NPR technology and convolutional neural networks (CNN) in computer vision are analyzed. Aiming at the features of ink texture images, a new sample-based ink texture synthesis method is proposed. The feature representation of ink texture is calculated using the CNN model, and then an ink texture with the same feature representation is generated on a random image. In addition, a synthesis method of ink painting picture is proposed based on the CNN. The results show that the ink texture generated by the ink texture synthesis algorithm is very good, and the Visual Geometry Group Network (VGG-Net) model shows the best generation effect. For images generated by high-level networks lack a lot of pixel information, but retain the main feature information of the image. When the learning rate is 10, the effect of the ink image synthesized based on the content image is slightly worse; and the image generated by the fusion of multiple styles confirms the feasibility of synthesizing ink images of different "sizes and styles". Therefore, this ink image synthesized on the basis of the CNN model shows a better effect, which extends the possibility of computer creation of richer ink painting works.

show abstract

StyleProp: Real‐time Example‐based Stylization of 3D Models

Abstract: can be rendered in real-time at arbitrary location within available interaction space (c, e, g) even on a mobile phone (i, j) while maintaining consistency when the viewing direction is changed. Style exemplar (b) courtesy of © Štěpánka Sýkorová.

Cited by 12 publications

References 56 publications

Art Museum Experience Application: Promoting Visitor Exploration of Mask Artifacts Through Stylization

Art Museum Experience Application: Promoting Visitor Exploration of Mask Artifacts Through Stylization

SNeRF: Stylized Neural Implicit Representations for 3D Scenes

Deep Learning in Computer Real-time Graphics and Image Using the Visual Effects of Non-photorealistic Rendering of Ink Painting

Contact Info

Product

Resources

About