Automatic pencil drawing generation using saliency map

Hata, Michitaka; Toyoura, Masahiro; Mao, Xiaoyang

doi:10.1145/2492494.2501878

Cited by 5 publications

(3 citation statements)

References 3 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Yang et al developed a swing bilateral LIC filter to control pencil drawing effects and remedy problems of existing convolution‐based schemes. Hata et al automatically converted an image into a pencil drawing with an accentuation effect that directs viewers' attention to important information. Lu et al first put stroke generation into a convolution framework to capture the essential characteristics of a pencil sketch and simulate the movement of a pencil while drawing and then used parametric histogram models to adjust the tone so that they can avoid artifacts caused by hatching.…”

Section: Related Workmentioning

confidence: 99%

“…Researchers have spent decades on achieving the more human hand‐drawn–like results from the natural image, but there is still a long way to go for getting a result that well matches the real pencil drawings' flexibility and precision, especially when the skill of artists' pencil drawing ability is highly developed. A good pencil drawing has to vividly exhibit the inner structure of a scene that cannot be achieved by common existing methods . In addition, the current pencil drawing of an artist usually looks real, which requires that a pencil drawing generation method has to generate a realistic pencil drawing result; however, the current pencil drawing stylization methods cannot realize it.…”

Section: Introductionmentioning

confidence: 99%

“…A good pencil drawing has to vividly exhibit the inner structure of a scene that cannot be achieved by common existing methods. [1][2][3][4] In addition, the current pencil drawing of an artist usually looks real, which requires that a pencil drawing generation method has to generate a realistic pencil drawing result; however, the current pencil drawing stylization methods [5][6][7][8] cannot realize it. Pencil drawing artists usually first draw some main coarse strokes to depict the main composition of the drawing and then gradually add smaller strokes to further refine the contours.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

SRNPD: Spatial rendering network for pencil drawing stylization

Jin

Sheng

et al. 2019

Computer Animation & Virtual

View full text Add to dashboard Cite

Pencil drawing is a simple yet effective way to depict what people see by clearly presenting details of the scene. Existing methods usually extract strokes of the input image and adjust the result image tone to make it look like a pencil drawing. However, they do not consider the quality of the stroke image and the geometry information of lines in the stroke image, which unavoidably results in the violation of original essential structures and in a flatten pencil drawing with unrealistic appearance. We put forward a spatial rendering network for pencil drawing stylization. Spatial stroke images are extracted from the image pyramid by a single‐shot bottom‐up neural network to improve the quality of these stroke images. Unlike the former tone adjustment–based methods, we analyze perceptual cues of strokes at different stroke image levels and use the obtained geometry information to constrain the stroke shading procedure. The final pencil drawing result is achieved by the stroke shading fusion of different levels' shading results. The effectiveness of our spatial rendering network for pencil drawing stylization is demonstrated by an ablation study, comparison to the state of the art, and a user study.

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

SRNPD: Spatial rendering network for pencil drawing stylization

Jin

Sheng

et al. 2019

Computer Animation & Virtual

View full text Add to dashboard Cite

show abstract

GAN-based pencil drawing learning system for art education on large-scale image datasets with learning analytics

Jin

Wang

et al. 2019

Interactive Learning Environments

View full text Add to dashboard Cite

We design a GAN-based pencil drawing learning system for art education on large image datasets to help students study how to draw pencil drawings for images and scenes. The system generates a pencil drawing result for a natural image based on generative adversarial network (GAN). The GAN network is trained on pencil drawing big datasets containing image pairs of natural images and their corresponding pencil drawings. Using the pencil drawing learning system, students can paint pencil drawings whenever they want and for whatever they like by uploading an image of the content they want to draw and getting a pencil drawing example of the uploaded image from the system. With the returned pencil drawing, students will see the pencil drawing effect of natural scenes clearly and realize how to draw the pencil drawing for the natural scene. Besides, with students using the pencil drawing learning system, it will be convenient for teachers assigning homework to students. Teachers can know the learning demands of students by evaluating the hand-in homework and update the content correspondingly. We have conducted two user studies for evaluating the practicality of the system, and the result of the two user studies demonstrated the applicability and practicality of the system.

show abstract

Parallel Fast Pencil Drawing Generation Algorithm Based on GPU

Qiu

Liu

et al. 2019

IEEE Access

View full text Add to dashboard Cite

With the development of image processing technology, pencil drawing has been widely used in video games and mobile phone applications. However, the existing pencil drawing algorithms require a large amount of time to convert a real picture into a pencil drawing; hence, it is difficult to apply them to real-time systems. This paper proposes a parallel fast pencil drawing generation algorithm based on the graphics processing unit (GPU) to accelerate the real-time rendering process of sketch painting. The parallelism of the pencil drawing generation algorithm is identified via a theoretical analysis at first. Then, sub-algorithms of the sequential algorithm are designed in parallel using the compute unified device architecture (CUDA) programming model and executed via thread-level parallel techniques. Furthermore, an optimal cache pattern of data that reduce the access time of the most frequently used data is structured using shared memory and constant memory. Finally, task-level parallelism is achieved by the CUDA stream technology, which overlaps independent sub-tasks for further acceleration. On the CUDA platform, the experimental results demonstrate that the proposed parallel algorithm can achieve a significant increase in speedup. The proposed algorithm achieves a performance improvement of 448.59 times compared with the sequential algorithm, on 2560×1920-resolution images, and maintains a high degree of similarity with the real pencil paintings. Hence, the proposed algorithm is suitable for real-time pencil drawing rendering and has promising application prospects in non-photorealistic rendering. INDEX TERMS Non-photorealistic rendering, pencil drawing, parallel algorithm, GPU platform, convolution operation, CUDA.

show abstract

Automatic pencil drawing generation using saliency map

Cited by 5 publications

References 3 publications

SRNPD: Spatial rendering network for pencil drawing stylization

SRNPD: Spatial rendering network for pencil drawing stylization

GAN-based pencil drawing learning system for art education on large-scale image datasets with learning analytics

Parallel Fast Pencil Drawing Generation Algorithm Based on GPU

Contact Info

Product

Resources

About