Delving into invisible semantics for generalized one-shot neural human rendering

Publication Type

Journal Article

Publication Date

10-2025

Abstract

Traditional human neural radiance fields often overlook crucial body semantics, resulting in ambiguous reconstructions, particularly in occluded regions. To address this problem, we propose the Super-Semantic Disentangled Neural Renderer (SSD-NeRF), which employs rich regional semantic priors to enhance human rendering accuracy. This approach initiates with a Visible-Invisible Semantic Propagation module, ensuring coherent semantic assignment to occluded parts based on visible body segments. Furthermore, a Region-Wise Texture Propagation module independently extends textures from visible to occluded areas within semantic regions, thereby avoiding irrelevant texture mixtures and preserving semantic consistency. Additionally, a view-aware curricular learning approach is integrated to bolster the model's robustness and output quality across different viewpoints. Extensive evaluations confirm that SSD-NeRF surpasses leading methods, particularly in generating quality and structurally semantic reconstructions of unseen or occluded views and poses.

Keywords

Neural radiance fields, human neural rendering, super-semantic disentanglement

Discipline

Graphics and Human Computer Interfaces | Software Engineering

Research Areas

Software and Cyber-Physical Systems

Publication

IEEE Transactions on Visualization and Computer Graphics

Volume

31

Issue

10

First Page

8070

Last Page

8084

ISSN

1077-2626

Identifier

10.1109/TVCG.2025.3563229

Publisher

Institute of Electrical and Electronics Engineers

Additional URL

https://doi.org/10.1109/TVCG.2025.3563229

This document is currently not available here.

Share

COinS