PI-REC: Progressive Image Reconstruction Network With Edge and Color Domain

arXiv 2019  ·  Sheng You, Ning You, Minxue Pan ·

We propose a universal image reconstruction method to represent detailed images purely from binary sparse edge and flat color domain. Inspired by the procedures of painting, our framework, based on generative adversarial network, consists of three phases: Imitation Phase aims at initializing networks, followed by Generating Phase to reconstruct preliminary images. Moreover, Refinement Phase is utilized to fine-tune preliminary images into final outputs with details. This framework allows our model generating abundant high frequency details from sparse input information. We also explore the defects of disentangling style latent space implicitly from images, and demonstrate that explicit color domain in our model performs better on controllability and interpretability. In our experiments, we achieve outstanding results on reconstructing realistic images and translating hand drawn drafts into satisfactory paintings. Besides, within the domain of edge-to-image translation, our model PI-REC outperforms existing state-of-the-art methods on evaluations of realism and accuracy, both quantitatively and qualitatively.

PDF Abstract

Datasets


Results from the Paper


Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Image Reconstruction Edge-to-Handbags PI-REC FID 0.069 # 1
LPIPS 0.168 # 4
HP 57.10 # 1
MMD 0.112 # 1
Image Reconstruction Edge-to-Shoes PI-REC FID 0.015 # 1
LPIPS 0.085 # 4
HP 62.30 # 1
MMD 0.081 # 1

Methods


No methods listed for this paper. Add relevant methods here