DivSwapper: Towards Diversified Patch-based Arbitrary Style Transfer

Yuan, Shuai; Dai, Aijun; Zhang, Yan; Liu, Ruixue; Chen, Meng; Chen, Baoyang; Qiu, Zhijie; He, Xiaodong

doi:10.24963/ijcai.2022/690

Cited by 8 publications

(8 citation statements)

References 3 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Furthermore, in existing transfer frameworks, VGG is also incorporated as part of the loss function to constrain the convergence of the neural network. [16], Micro [21], PAMA [14], AdaIN [8], and RCST(our proposed) algorithms.…”

Section: Related Workmentioning

confidence: 99%

“…Firstly, we qualitatively compared the results of various style transfer algorithms, such as [8], [21], [14], [16], [], under different content and style combinations. As shown in Figure 2, our proposed algorithm demonstrates strong regional characteristics in the transferred textures.…”

Section: A Comparative Experimentsmentioning

confidence: 99%

“…In the given images, (a) depicts the effectiveness of Microast [21], whereas (b) illustrates the outcomes of our proposed algorithm Abstract-Image style transfer is a challenging task in computational vision. Existing algorithms transfer the color and texture of style images by controlling the neural network's feature layers.…”

mentioning

confidence: 99%

“…Fig.2. The image presents the results of comparative experiments on different content and style datasets for the LDaeURFST[16], Micro[21], PAMA[14], AdaIN[8], and RCST(our proposed) algorithms.…”

mentioning

confidence: 99%

See 3 more Smart Citations

Neural Style Transfer for 3d Meshes

Kang

Xiao

Cao

et al. 2023

Preprint

View full text Add to dashboard Cite

Section: Related Workmentioning

confidence: 99%

Section: A Comparative Experimentsmentioning

confidence: 99%

mentioning

confidence: 99%

mentioning

confidence: 99%

See 2 more Smart Citations

Neural Style Transfer for 3d Meshes

Kang

Xiao

Cao

et al. 2023

Preprint

View full text Add to dashboard Cite

“…Simply transferring the global style to the content image considers neither the diversity of local style patterns nor the difference among multiple content regions (e.g., AdaIN [15] fails to capture the abundant style information in the 1 𝑠𝑡 row of Figure 1). In contrast, local patch-based methods [3,7,27,35,38,44,51,53] conduct style transfer by replacing every content patch with similar style patches in the feature space. For example, Chen et al [7] performed a style-swap operation that swaps each content feature patch with its closest-matching style feature patch, and Park et al [35] introduced a style-attentional network that integrates the style feature patches according to the semantic spatial distribution of the content image.…”

Section: Introductionmentioning

confidence: 99%

TSSAT: Two-Stage Statistics-Aware Transformation for Artistic Style Transfer

Chen,

Zhao,

et al. 2023

Proceedings of the 31st ACM International Conference on Multimedia

Self Cite

View full text Add to dashboard Cite

Artistic style transfer aims to create new artistic images by rendering a given photograph with the target artistic style. Existing methods learn styles simply based on global statistics or local patches, lacking careful consideration of the drawing process in practice. Consequently, the stylization results either fail to capture abundant and diversified local style patterns, or contain undesired semantic information of the style image and deviate from the global style distribution. To address this issue, we imitate the drawing process of humans and propose a Two-Stage Statistics-Aware Transformation (TSSAT) module, which first builds the global style foundation by aligning the global statistics of content and style features and then further enriches local style details by swapping the local statistics (instead of local features) in a patch-wise manner, significantly improving the stylization effects. Moreover, to further enhance both content and style representations, we introduce two novel losses: an attention-based content loss and a patch-based style loss, where the former enables better content preservation by enforcing the semantic relation in the content image to be retained during stylization, and the latter focuses on increasing the local style similarity between the style and stylized images. Extensive qualitative and quantitative experiments verify the effectiveness of our method. CCS CONCEPTS• Applied computing → Fine arts; • Computing methodologies → Appearance and texture representations; Image manipulation.

show abstract

PKD‐Net: Distillation of prior knowledge for image completion by multi‐level semantic attention

Lu,

Lin,

Xing

et al. 2023

Concurrency and Computation

View full text Add to dashboard Cite

SummaryPrior knowledge plays a crucial role in image completion. Although almost all of the existing image completion methods use prior knowledge to complete the image to be repaired from different perspectives, the learning and modeling of the prior knowledge is still a challenging problem. In order to address this issue, we propose a novel prior knowledge distillation framework (PKD‐Net) which could distill prior knowledge of structure and style from multiple semantic space and generates not only plausible content but also consistent style with surrounding image area. Our PKD‐Net replaces the skip connection in the vanilla U‐Net with a semantic shift attention module. The semantic shift attention module takes features from encoder layer and those from decoder layer as input pairs to output shifted features which take into account the long‐range dependency of encoder layer features and corresponding decoder layer features from the perspective of local structure and style. Semantic shift attention module models the global interdependencies in local spatial structures (patches centered at each position) and style (appearance texture) dimensions respectively, which could implement distillation of prior knowledge from two aspects: structure and style. Experiments on multiple datasets including faces (CelebA, CelebA‐HQ) and natural images (ImageNet, Places2, Paris Street View) demonstrate that our proposed approach generates higher quality completion results than existing ones.

show abstract

DivSwapper: Towards Diversified Patch-based Arbitrary Style Transfer

Cited by 8 publications

References 3 publications

Neural Style Transfer for 3d Meshes

Neural Style Transfer for 3d Meshes

TSSAT: Two-Stage Statistics-Aware Transformation for Artistic Style Transfer

PKD‐Net: Distillation of prior knowledge for image completion by multi‐level semantic attention

Contact Info

Product

Resources

About