NOVA: NOvel View Augmentation for Neural Composition of Dynamic Objects

Dakshit Agrawal, Jiajie Xu, Siva Karthik Mustikovela, Ioannis Gkioulekas, Ashish Shrivastava, Yuning Chai; Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV) Workshops, 2023, pp. 4288-4292

Abstract

We propose a novel-view augmentation (NOVA) strategy to train NeRFs for photo-realistic 3D composition of dynamic objects in a static scene. Compared to prior work, our framework significantly reduces blending artifacts when inserting multiple dynamic objects into a 3D scene at novel views and times; achieves comparable PSNR without the need for additional ground truth modalities like optical flow; and overall provides ease, flexibility, and scalability in neural composition. Our codebase is on GitHub.

Related Material

[pdf] [arXiv]
[bibtex]
@InProceedings{Agrawal_2023_ICCV, author = {Agrawal, Dakshit and Xu, Jiajie and Mustikovela, Siva Karthik and Gkioulekas, Ioannis and Shrivastava, Ashish and Chai, Yuning}, title = {NOVA: NOvel View Augmentation for Neural Composition of Dynamic Objects}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV) Workshops}, month = {October}, year = {2023}, pages = {4288-4292} }