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

The neural rendering of humans is a topic of great research significance.However, previous works mostly focus on achieving photorealistic details,neglecting the exploration of human parsing. Additionally, classical semanticwork are all limited in their ability to efficiently represent fine results incomplex motions. Human parsing is inherently related to radiancereconstruction, as similar appearance and geometry often correspond to similarsemantic part. Furthermore, previous works often design a motion field thatmaps from the observation space to the canonical space, while it tends toexhibit either underfitting or overfitting, resulting in limitedgeneralization. In this paper, we present Semantic-Human, a novel method thatachieves both photorealistic details and viewpoint-consistent human parsing forthe neural rendering of humans. Specifically, we extend neural radiance fields(NeRF) to jointly encode semantics, appearance and geometry to achieve accurate2D semantic labels using noisy pseudo-label supervision. Leveraging theinherent consistency and smoothness properties of NeRF, Semantic-Human achievesconsistent human parsing in both continuous and novel views. We also introduceconstraints derived from the SMPL surface for the motion field andregularization for the recovered volumetric geometry. We have evaluated themodel using the ZJU-MoCap dataset, and the obtained highly competitive resultsdemonstrate the effectiveness of our proposed Semantic-Human. We also showcasevarious compelling applications, including label denoising, label synthesis andimage editing, and empirically validate its advantageous properties.

Semantic-Human: Neural Rendering of Humans from Monocular Video with Human Parsing