English

Sem2NeRF: Converting Single-View Semantic Masks to Neural Radiance Fields

Computer Vision and Pattern Recognition 2023-04-04 v2 Artificial Intelligence Graphics

Abstract

Image translation and manipulation have gain increasing attention along with the rapid development of deep generative models. Although existing approaches have brought impressive results, they mainly operated in 2D space. In light of recent advances in NeRF-based 3D-aware generative models, we introduce a new task, Semantic-to-NeRF translation, that aims to reconstruct a 3D scene modelled by NeRF, conditioned on one single-view semantic mask as input. To kick-off this novel task, we propose the Sem2NeRF framework. In particular, Sem2NeRF addresses the highly challenging task by encoding the semantic mask into the latent code that controls the 3D scene representation of a pre-trained decoder. To further improve the accuracy of the mapping, we integrate a new region-aware learning strategy into the design of both the encoder and the decoder. We verify the efficacy of the proposed Sem2NeRF and demonstrate that it outperforms several strong baselines on two benchmark datasets. Code and video are available at https://donydchen.github.io/sem2nerf/

Keywords

Cite

@article{arxiv.2203.10821,
  title  = {Sem2NeRF: Converting Single-View Semantic Masks to Neural Radiance Fields},
  author = {Yuedong Chen and Qianyi Wu and Chuanxia Zheng and Tat-Jen Cham and Jianfei Cai},
  journal= {arXiv preprint arXiv:2203.10821},
  year   = {2023}
}

Comments

ECCV2022, Code: https://github.com/donydchen/sem2nerf Project Page: https://donydchen.github.io/sem2nerf/

R2 v1 2026-06-24T10:20:10.312Z