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

In this paper, we propose StereoPIFu, which integrates the geometricconstraints of stereo vision with implicit function representation of PIFu, torecover the 3D shape of the clothed human from a pair of low-cost rectifiedimages. First, we introduce the effective voxel-aligned features from a stereovision-based network to enable depth-aware reconstruction. Moreover, the novelrelative z-offset is employed to associate predicted high-fidelity human depthand occupancy inference, which helps restore fine-level surface details.Second, a network structure that fully utilizes the geometry information fromthe stereo images is designed to improve the human body reconstruction quality.Consequently, our StereoPIFu can naturally infer the human body's spatiallocation in camera space and maintain the correct relative position ofdifferent parts of the human body, which enables our method to capture humanperformance. Compared with previous works, our StereoPIFu significantlyimproves the robustness, completeness, and accuracy of the clothed humanreconstruction, which is demonstrated by extensive experimental results.

StereoPIFu: Depth Aware Clothed Human Digitization via Stereo Vision