NOVA：面向动态对象神经合成的新型视角增强
计算机视觉与模式识别
2023-08-25 v1
摘要
我们提出一种新型视角增强（NOVA）策略，用于训练NeRF以实现静态场景中动态对象的照片级真实3D合成。相较先前工作，我们的框架在将多个动态对象插入至新视角与新时刻的3D场景时显著减少混合伪影；无需光流等额外真值模态即可达到可比的PSNR；且总体上在神经合成中提供易用性、灵活性与可扩展性。我们的代码库已发布于GitHub。
引用
@article{arxiv.2308.12560,
title = {NOVA: NOvel View Augmentation for Neural Composition of Dynamic Objects},
author = {Dakshit Agrawal and Jiajie Xu and Siva Karthik Mustikovela and Ioannis Gkioulekas and Ashish Shrivastava and Yuning Chai},
journal= {arXiv preprint arXiv:2308.12560},
year = {2023}
}
备注
Accepted for publication in ICCV Computer Vision for Metaverse Workshop 2023 (code is available at https://github.com/dakshitagrawal/NoVA)