Implicit Subspace Prior Learning for Dual-Blind Face Restoration

by   Lingbo Yang, et al.

Face restoration is an inherently ill-posed problem, where additional prior constraints are typically considered crucial for mitigating such pathology. However, real-world image prior are often hard to simulate with precise mathematical models, which inevitably limits the performance and generalization ability of existing prior-regularized restoration methods. In this paper, we study the problem of face restoration under a more practical “dual blind” setting, i.e., without prior assumptions or hand-crafted regularization terms on the degradation profile or image contents. To this end, a novel implicit subspace prior learning (ISPL) framework is proposed as a generic solution to dual-blind face restoration, with two key elements: 1) an implicit formulation to circumvent the ill-defined restoration mapping and 2) a subspace prior decomposition and fusion mechanism to dynamically handle inputs at varying degradation levels with consistent high-quality restoration results. Experimental results demonstrate significant perception-distortion improvement of ISPL against existing state-of-the-art methods for a variety of restoration subtasks, including a 3.69db PSNR and 45.8 ESRGAN, the 2018 NTIRE SR challenge winner. Overall, we prove that it is possible to capture and utilize prior knowledge without explicitly formulating it, which will help inspire new research paradigms towards low-level vision tasks.


page 2

page 3

page 7

page 8

page 10

page 11

page 12

page 14


Blind Image Restoration without Prior Knowledge

Many image restoration techniques are highly dependent on the degradatio...

Towards Robust Blind Face Restoration with Codebook Lookup Transformer

Blind face restoration is a highly ill-posed problem that often requires...

HiFaceGAN: Face Renovation via Collaborative Suppression and Replenishment

Existing face restoration researches typically relies on either the degr...

Universal Face Restoration With Memorized Modulation

Blind face restoration (BFR) is a challenging problem because of the unc...

Learning Dual Memory Dictionaries for Blind Face Restoration

To improve the performance of blind face restoration, recent works mainl...

Blind Face Restoration: Benchmark Datasets and a Baseline Model

Blind Face Restoration (BFR) aims to construct a high-quality (HQ) face ...

Blind Image Restoration with Flow Based Priors

Image restoration has seen great progress in the last years thanks to th...

Please sign up or login with your details

Forgot password? Click here to reset