DanbooRegion: An Illustration Region Dataset

Zhang, Lvmin; Liu, Chunping

doi:10.1007/978-3-030-58601-0_9

Cited by 15 publications

(9 citation statements)

References 47 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Within the problem of stylized reconstruction, we solve the task of contour removal from illustrations. There is much work on line extraction [21,38], sketch simplification [33,34], reconstruction from lines [11,24], line exploits for artistic imagery [6,41], and scratch-line removal [8,27,29,32,35]; however, the removal of lines from linebased illustration has seen little focus. We examine this contour deletion task in the context of adapting drawings to render-like images more conducive to 3D reconstruction; we find that naive image-to-image translation [19,45] is unsuited to the task, and propose a simple yet effective adversarial training setup with facial feature awareness.…”

Section: Anime-style 3d Avatars and Illustrationsmentioning

confidence: 99%

Enterprises Build Sustainable Innovation Loop: Take ByteDance Launching Lark as an Example

Chen

2023

Frontiers in Artificial Intelligence and Applications

View full text Add to dashboard Cite

This paper uses the method of formal model construction to model the path of enterprise sustainable innovation and explains it by case analysis. Some suggestions are put forward then. In the changing market environment, enterprises can adapt to and strive for more living space only through continuous innovation. The construction of a sustainable innovation loop makes the previous research on sustainable innovation become relatively concrete from the abstract. Enterprises should construct and complete the loop of innovation path according to their own characteristics. In the process of launching Lark, ByteDance takes scientific and technological innovation as the basis, and business model innovation as the key link, and finally completes the cycle of innovation path, and the innovation is still ongoing, achieving the purpose of sustainable innovation, reflecting the enterprise innovation strategy and corporate culture.

show abstract

Section: Anime-style 3d Avatars and Illustrationsmentioning

confidence: 99%

Enterprises Build Sustainable Innovation Loop: Take ByteDance Launching Lark as an Example

Chen

2023

Frontiers in Artificial Intelligence and Applications

View full text Add to dashboard Cite

show abstract

“…DanbooRegion [ZJL20] aims at extracting regions from illustrations and cartoon images. The DanbooRegion dataset provides paired illustrations and region maps.…”

Section: Line Art Segmentationmentioning

confidence: 99%

“…Given that we are able to use the trained model from DanbooRegion [ZJL20] to extract the region maps from line art images, it is straightforward to input such regional information to the network directly to serve as extra guidance for colorization. As shown in Figure 2-(a), we first use the U-Net type network with the trained weights to produce a skeleton map ŝ from the input line art, and then concatenate the line art image and the skeleton map directly.…”

Section: Direct Concatenationmentioning

confidence: 99%

“…The total losses for discriminator and generator at colorization step are respectively defined as: Ground truth skeleton maps are required for the segmentation branch in the "Dual-branch" fusion mode. We notice a recent dataset DanbooRegion [ZJL20], which is built on the Danbooru dataset with region annotations for illustrations. However, it lacks the tag information and loses the identity mapping to the original dataset, and thus is not practical in our experiments.…”

Section: Loss Functionmentioning

confidence: 99%

See 1 more Smart Citation

Line Art Colorization Based on Explicit Region Segmentation

Cao

Gao

2021

Computer Graphics Forum

View full text Add to dashboard Cite

Automatic line art colorization plays an important role in anime and comic industry. While existing methods for line art colorization are able to generate plausible colorized results, they tend to suffer from the color bleeding issue. We introduce an explicit segmentation fusion mechanism to aid colorization frameworks in avoiding color bleeding artifacts. This mechanism is able to provide region segmentation information for the colorization process explicitly so that the colorization model can learn to avoid assigning the same color across regions with different semantics or inconsistent colors inside an individual region. The proposed mechanism is designed in a plug‐and‐play manner, so it can be applied to a diversity of line art colorization frameworks with various kinds of user guidances. We evaluate this mechanism in tag‐based and reference‐based line art colorization tasks by incorporating it into the state‐of‐the‐art models. Comparisons with these existing models corroborate the effectiveness of our method which largely alleviates the color bleeding artifacts. The code is available at https://github.com/Ricardo-L-C/ColorizationWithRegion.

show abstract

“…While both designs require the pretrained Mask R-CNN components during training, feature matching discards them during inference, instead relying on the trained matcher network. [55], painting relighting [57], image-to-image translation with photos [26], and keyframe interpolation [44].…”

Section: The Illustration Domainmentioning

confidence: 99%

Transfer Learning for Pose Estimation of Illustrated Characters

Chen¹,

Zwicker²

2021

Preprint

View full text Add to dashboard Cite

Human pose information is a critical component in many downstream image processing tasks, such as activity recognition and motion tracking. Likewise, a pose estimator for the illustrated character domain would provide a valuable prior for assistive content creation tasks, such as reference pose retrieval and automatic character animation. But while modern data-driven techniques have substantially improved pose estimation performance on natural images, little work has been done for illustrations. In our work, we bridge this domain gap by efficiently transfer-learning from both domain-specific and task-specific source models. Additionally, we upgrade and expand an existing illustrated pose estimation dataset, and introduce two new datasets for classification and segmentation subtasks. We then apply the resultant state-of-the-art character pose estimator to solve the novel task of pose-guided illustration retrieval. All data, models, and code will be made publicly available.

show abstract

DanbooRegion: An Illustration Region Dataset

Cited by 15 publications

References 47 publications

Enterprises Build Sustainable Innovation Loop: Take ByteDance Launching Lark as an Example

Enterprises Build Sustainable Innovation Loop: Take ByteDance Launching Lark as an Example

Line Art Colorization Based on Explicit Region Segmentation

Transfer Learning for Pose Estimation of Illustrated Characters

Contact Info

Product

Resources

About