English

Neural Implicit Field Editing Considering Object-environment Interaction

Computer Vision and Pattern Recognition 2023-11-02 v1 Artificial Intelligence

Abstract

The 3D scene editing method based on neural implicit field has gained wide attention. It has achieved excellent results in 3D editing tasks. However, existing methods often blend the interaction between objects and scene environment. The change of scene appearance like shadows is failed to be displayed in the rendering view. In this paper, we propose an Object and Scene environment Interaction aware (OSI-aware) system, which is a novel two-stream neural rendering system considering object and scene environment interaction. To obtain illuminating conditions from the mixture soup, the system successfully separates the interaction between objects and scene environment by intrinsic decomposition method. To study the corresponding changes to the scene appearance from object-level editing tasks, we introduce a depth map guided scene inpainting method and shadow rendering method by point matching strategy. Extensive experiments demonstrate that our novel pipeline produce reasonable appearance changes in scene editing tasks. It also achieve competitive performance for the rendering quality in novel-view synthesis tasks.

Keywords

Cite

@article{arxiv.2311.00425,
  title  = {Neural Implicit Field Editing Considering Object-environment Interaction},
  author = {Zhihong Zeng and Zongji Wang and Yuanben Zhang and Weinan Cai and Zehao Cao and Lili Zhang and Yan Guo and Yanhong Zhang and Junyi Liu},
  journal= {arXiv preprint arXiv:2311.00425},
  year   = {2023}
}
R2 v1 2026-06-28T13:08:25.046Z