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

It is very challenging to accurately reconstruct sophisticated human geometrycaused by various poses and garments from a single image. Recently, works basedon pixel-aligned implicit function (PIFu) have made a big step and achievedstate-of-the-art fidelity on image-based 3D human digitization. However, thetraining of PIFu relies heavily on expensive and limited 3D ground truth data(i.e. synthetic data), thus hindering its generalization to more diverse realworld images. In this work, we propose an end-to-end self-supervised networknamed SelfPIFu to utilize abundant and diverse in-the-wild images, resulting inlargely improved reconstructions when tested on unconstrained in-the-wildimages. At the core of SelfPIFu is the depth-guided volume-/surface-awaresigned distance fields (SDF) learning, which enables self-supervised learningof a PIFu without access to GT mesh. The whole framework consists of a normalestimator, a depth estimator, and a SDF-based PIFu and better utilizes extradepth GT during training. Extensive experiments demonstrate the effectivenessof our self-supervised framework and the superiority of using depth as input.On synthetic data, our Intersection-Over-Union (IoU) achieves to 93.5%, 18%higher compared with PIFuHD. For in-the-wild images, we conduct user studies onthe reconstructed results, the selection rate of our results is over 68%compared with other state-of-the-art methods.

PIFu for the Real World: A Self-supervised Framework to Reconstruct Dressed Human from Single-view Images