Author Affiliations
College of Electronics and Information Engineering, Lanzhou Jiaotong University, Lanzhou, Gansu 730070, Chinashow less
Fig. 1. Network framework diagram
Fig. 2. VGG-19 network feature extraction
Fig. 3. Representation of foreground and background of the image
Fig. 4. Linear combination of mask color channels
Fig. 5. Deep matting network structure
Fig. 6. Comparison of matting effects. (a1) (a2) Original images; (b1) (b2) Trimap; (c1) (c2) traditional matting; (d1) (d2) depth matting of this paper
Fig. 7. Transform network structure
Fig. 8. Comparison of style transfer texture of different convolution kernels. (a1)(a2) Content images; (b1)(b2) style images; (c1)(c2) 7×7 convolution kernel transfer texture; (d1)(d2) 3×3 convolution kernel transfer texture
Fig. 9. Graphs of loss functions. (a) Content image; (b) style image
Fig. 10. Texture comparison. (a1)(a2) Content images; (b1)(b2) style images; (c1)(c2) before normalization; (d1)(d2) after normalization
Fig. 11. Effect of style and content trade-off.(a) η=0; (b) η=0.25; (c)η=0.50; (d) η=0.75; (e) η=1.00; (f) style image
Fig. 12. Transfer results of this article
Fig. 13. Comparison of experimental results. (a1)--(a4) Content images; (b1)--(b4) style images; (c1)--(c4) images based on method proposed by Gatys
et al[5]; (d1)--(d4) images based on method proposed by Ulyanov
et al[10]; (e1)--(e4) images based on method proposed by Huang
et al[12]; (f1)--(f4) images based on method proposed by Chen
et al[26]; (g1)--(g4) images based on method proposed by Li
et al[27]; (h1)--(h4) images based on our method
Fig. 14. Objective evaluation. (a) MSSIM; (b) PSNR; (c) AvG; (d) QAB/F
Layer | Conv1 | Conv2 | Conv3 | Conv4 | Conv5 |
---|
Stride | 1 | 2 | 4 | 8 | 16 | Receptive field | 5 | 14 | 40 | 92 | 196 |
|
Table 1. Stride length and receptive field parameter settings
Layer | Output size | Size, Stride | Depth | Parameter |
---|
Input | 224×224×3 | | | | Conv1 | 111×111×9 | 3×3×3, 2(×96) | 1 | 10728 | Maxpool1 | 55×55×96 | 3×3, 2 | 0 | | Fire2, Fire3 | 55×55×128 | | 2 | 12004 | Fire4 | 55×55×256 | | 2 | 20646 | Avgpool4 | 27×27×256 | 3×3, 2 | 0 | | Fire5 | 27×27×256 | | 2 | 24742 | Fire6, Fire7 | 27×27×384 | | 2 | 90936 | Fire8 | 27×27×512 | | 2 | 77581 | Maxpool8 | 13×12×512 | 3×3, 2 | 0 | | Fire9 | 13×13×512 | | 2 | 77581 | Conv10 | 13×13×1000 | 1×1, 1(×1000) | 1 | 103400 | Avgpool10 | 1×1×1000 | 13×13, 1 | 0 | |
|
Table 2. Transfer network parameters