English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Face frontalization refers to the process of synthesizing the frontal view ofa face from a given profile. Due to self-occlusion and appearance distortion inthe wild, it is extremely challenging to recover faithful results and preservetexture details in a high-resolution. This paper proposes a High Fidelity PoseInvariant Model (HF-PIM) to produce photographic and identity-preservingresults. HF-PIM frontalizes the profiles through a novel texture warpingprocedure and leverages a dense correspondence field to bind the 2D and 3Dsurface spaces. We decompose the prerequisite of warping into densecorrespondence field estimation and facial texture map recovering, which areboth well addressed by deep networks. Different from those reconstructionmethods relying on 3D data, we also propose Adversarial Residual DictionaryLearning (ARDL) to supervise facial texture map recovering with only monocularimages. Exhaustive experiments on both controlled and uncontrolled environmentsdemonstrate that the proposed method not only boosts the performance ofpose-invariant face recognition but also dramatically improves high-resolutionfrontalization appearances.

Learning a High Fidelity Pose Invariant Model for High-resolution Face Frontalization