Wang C, Zheng H, Yu Z, et al. Discriminative region proposal adversarial networks for high-quality image-to-image translation[C]//Proceedings of the European Conference on Computer Vision (ECCV). 2018: 770-785.
1. Overview
论文提出Discriminative Region Proposal Adversarial Network (DRPAN)结构,并用于一些任务
- de-raining
- image-to-image translation
1.1. 模型
1.1.1. Discriminator
generate score map
find the most artificial patch by sliding window
- map the patch into the real image, generate fake-mask real
- w. sliding window size
- w_s. score map size
- w_i. input image size
- w_*. patch size of input image that window map to
- x_c, y_c. center point of score map patch
- τ. scale
- d_r. discriminate region of input image
1.1.2. Reviser
- discriminate
1.2. Loss Function
Discriminator
Reviser
δ. noiseGenerator
1.3. Algorithm
1.4. 数据集
- Cityscapes
- Facades
- SUN6
- UT Zappos 50K
- edge to handbag
1.5. Related Work
- ID-CGAN
- Pix2Pix
- CRN (cascaded refined network)
1.6. Metric
- PSNR
- SSIM
- VIF
- RECO
- IOU
- FCN-score
- AMT
- Inception score