Facial Attribute Capsules for Noise Face Super Resolution

TL;DR

This paper introduces a novel Facial Attribute Capsules Network (FACN) that enhances noise-robustness in high-scale face super-resolution by modeling facial attributes through semantic and probabilistic capsules, outperforming existing methods.

Contribution

The paper proposes a new capsule-based model for noise-robust face super-resolution, integrating semantic and probabilistic facial attributes for improved image reconstruction.

Findings

Outperforms state-of-the-art methods on low-resolution noisy face images.

Achieves superior hallucination results in benchmark tests.

Demonstrates robustness to noise in face super-resolution tasks.

Abstract

Existing face super-resolution (SR) methods mainly assume the input image to be noise-free. Their performance degrades drastically when applied to real-world scenarios where the input image is always contaminated by noise. In this paper, we propose a Facial Attribute Capsules Network (FACN) to deal with the problem of high-scale super-resolution of noisy face image. Capsule is a group of neurons whose activity vector models different properties of the same entity. Inspired by the concept of capsule, we propose an integrated representation model of facial information, which named Facial Attribute Capsule (FAC). In the SR processing, we first generated a group of FACs from the input LR face, and then reconstructed the HR face from this group of FACs. Aiming to effectively improve the robustness of FAC to noise, we generate FAC in semantic, probabilistic and facial attributes manners by means of integrated learning strategy. Each FAC can be divided into two sub-capsules: Semantic Capsule (SC) and Probabilistic Capsule (PC). Them describe an explicit facial attribute in detail from two aspects of semantic representation and probability distribution. The group of FACs model an image as a combination of facial attribute information in the semantic space and probabilistic space by an attribute-disentangling way. The diverse FACs could better combine the face prior information to generate the face images with fine-grained semantic attributes. Extensive benchmark experiments show that our method achieves superior hallucination results and outperforms state-of-the-art for very low resolution (LR) noise face image super resolution.