Towards Real-World Blind Face Restoration with Generative Facial Prior

Yu Li, Ying Shan, Xintao Wang, Honglun Zhang

Code that ran

We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. If it links a repository, it is listed below.

Repositories linked to this paper

TencentARC/GFPGAN — marked official in Papers with Code; named in the paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

ECCV 20 Figure 1: Comparisons with state-of-the-art face restoration methods: HiFaceGAN [67], DFDNet [44], Wan et al. [61] and PULSE [52] on the real-world low-quality images. While previous methods struggle to restore faithful facial details or retain face identity, our proposed GFP-GAN achieves a good balance of realness and fidelity with much less artifacts. In addition, the powerful generative facial prior allows us to perform restoration and color enhancement jointly.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2101.04061")
get_code_for_paper("2101.04061")
have("2101.04061")

Connect an agent — have() is free.