Facial Feature Model for a Portrait Video Stylization

Liang, Dongxue; Park, Kyoungju; Krompiec, Przemyslaw

doi:10.3390/sym10100442

Cited by 4 publications

(3 citation statements)

References 42 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Berger et al [3] proposed a data-driven approach to learn the portrait sketching style, by analyzing strokes and geometric shapes in a collection of artists' sketch data. Liang et al [19] proposed a method for portrait video stylization by generating a facial feature model using extended Mask R-CNN and applying two stroke rendering methods on sub-regions. The above methods generate results of a specific type of art, e.g., curved brush stroke portrait, portrait sketching.…”

Section: Non-photorealistic Rendering Of Portraitsmentioning

confidence: 99%

APDrawingGAN: Generating Artistic Portrait Drawings From Face Photos With Hierarchical GANs

Liu

Lai

et al. 2019

2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)

139

105

View full text Add to dashboard Cite

Drawing by an artist (a) An image pair in the training set (c) Existing methods APDrawingGAN Headshot Portrait CycleGAN Pix2Pix A test photo Output (b) Our method Deep Image Analogy CNNMRF Gatys The results of using the same input test photo of Barack Obama Figure 1: (a) An artist draws a portrait drawing using a sparse set of lines and very few shaded regions to capture the distinctive appearance of a given face photo. (b) Our APDrawingGAN learns this artistic drawing style and automatically transforms a face photo into a high-quality artistic portrait drawing. (c) Using the same input face photo, six state-of-the-art style transfer methods cannot generate desired artistic drawings: Deep Image Analogy [20], CNNMRF [18], Gatys [11] and Headshot Portrait [32] change facial features or fail to capture style, CycleGAN [40] and Pix2Pix [15] produce false details around hair, eyes or corners of the mouth.

show abstract

Section: Non-photorealistic Rendering Of Portraitsmentioning

confidence: 99%

APDrawingGAN: Generating Artistic Portrait Drawings From Face Photos With Hierarchical GANs

Liu

Lai

et al. 2019

2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)

139

105

View full text Add to dashboard Cite

show abstract

“…The main idea of Mask RCNN is to locate multiple feature regions in an image, input each region into CNN for feature extraction [16] and generate a Mask on the feature-extracted region. The biggest feature of Mask RCNN is to separately extract the classified regression information of the image to be tested (that is, the border information of the target to be tested) and combine it with the pyramid features (the length and width of the image input for pyramid region of interest [ROI] processing, that is, PyramidROIAlign) for mask generation, which is shown in Figure 1.…”

Section: Related Workmentioning

confidence: 99%

A Ship Target Location and Mask Generation Algorithms Base on Mask RCNN

Shaodan¹,

Feng²,

Chen³

2019

IJCIS

View full text Add to dashboard Cite

Ship detection is a canonical problem in computer vision. Motivated by the observation that the major bottleneck of ship detection lies on the different scales of ship instances in images, we focus on improving the detection rate, especially for the smallsized ships which are relatively far from the camera. We use the Smooth function combined with L1 and L2 norm to optimize the region proposal network (RPN) loss function and reduce the deviation between the prediction frame and the actual target to ensure the accurate location of the ship target. With the Two-Way sampling combined with the shared weight to generate the mask, we solve the problems of inaccurate segmentation, target loss and small interference when Mask Region Convolution Neural Network (RCNN) is used to segment an instance. We create the experimental data sets from the deep learning annotation tool-Labelme. Experiments show that the improved Mask-RCNN model has a confidence rate of 82.17%. Serving as the basic network, the test accuracy rate of ResNetXt-101 is 3.3% higher than that of the original ResNet-101, which can better realize the function of ship target location and mask generation.

show abstract

“…Many relevant research studies have been reported and many algorithms have been proposed that achieve a satisfactory visual effect [29]- [34]. In [32], Liang et al proposed a method for automatically stylizing portrait videos that contain small human faces that extends the mask regions with the convolutional neural network (R-CNN) features. The experimental results demonstrated that the method could effectively preserve the small and distinct facial features.…”

Section: Related Workmentioning

confidence: 99%

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

Facial Feature Model for a Portrait Video Stylization

Cited by 4 publications

References 42 publications

APDrawingGAN: Generating Artistic Portrait Drawings From Face Photos With Hierarchical GANs

APDrawingGAN: Generating Artistic Portrait Drawings From Face Photos With Hierarchical GANs

A Ship Target Location and Mask Generation Algorithms Base on Mask RCNN

Parallel Fast Pencil Drawing Generation Algorithm Based on GPU

Contact Info

Product

Resources

About