Combining Generative and Geometry Priors for Wide-Angle Portrait Correction

TL;DR

This paper introduces a novel method combining generative face priors and geometric symmetry constraints to improve wide-angle portrait correction, resulting in more natural and visually appealing images.

Contribution

It proposes a new approach that integrates generative face priors with symmetry constraints to enhance correction quality in wide-angle portrait images.

Findings

Outperforms previous methods significantly in quantitative metrics.

Achieves superior perceptual visual quality.

Effectively enforces symmetry for natural correction.

Abstract

Wide-angle lens distortion in portrait photography presents a significant challenge for capturing photo-realistic and aesthetically pleasing images. Such distortions are especially noticeable in facial regions. In this work, we propose encapsulating the generative face prior as a guided natural manifold to facilitate the correction of facial regions. Moreover, a notable central symmetry relationship exists in the non-face background, yet it has not been explored in the correction process. This geometry prior motivates us to introduce a novel constraint to explicitly enforce symmetry throughout the correction process, thereby contributing to a more visually appealing and natural correction in the non-face region. Experiments demonstrate that our approach outperforms previous methods by a large margin, excelling not only in quantitative measures such as line straightness and shape consistency metrics but also in terms of perceptual visual quality. All the code and models are available at https://github.com/Dev-Mrha/DualPriorsCorrection.