Generative Rendering Network based on U-shape Discriminator. Issue 1 (1st June 2022)

• Record Type: Journal Article
• Authors: Mu, Chen; Zhao, Huaici; Liu, Pengfei
• Is Part Of: Journal of physics. Volume 2284:Issue 1(2022)
• Publication Date: 2022-06-01
• Subjects: Physics -- Congresses; 530.5
• DOI: 10.1088/1742-6596/2284/1/012005
• Languages: English
• ISSNs: 1742-6588

Abstract

Abstract: This paper introduces a generative rendering network(GRN) based on a U-shape discriminator for novel view image synthesis. Recently, some generative adversarial networks start to explore 3D space and synthesize new images by rendering methods. Compared with 2D-only networks, they have achieved impressive results in synthesizing novel view images. However, they still have a common shortcoming: the discriminator cannot provide more detailed information for training a strong generator. For this problem, we design an U-shape based discriminator to extract both global information and pixel-wise information. This innovative discriminator will feedback more instructive clues to train a better generator. Benefit from this strategy, our synthesis results on ShapeNet v2 "cars" and "chairs" and celebA have achieved better performance than comparative methods.