Bibliographic Details
| Title: |
NOVA: NOvel View Augmentation for Neural Composition of Dynamic Objects |
| Authors: |
Agrawal, Dakshit, Xu, Jiajie, Mustikovela, Siva Karthik, Gkioulekas, Ioannis, Shrivastava, Ashish, Chai, Yuning |
| Publication Year: |
2023 |
| Collection: |
Computer Science |
| Subject Terms: |
Computer Science - Computer Vision and Pattern Recognition |
| More Details: |
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.
Comment: Accepted for publication in ICCV Computer Vision for Metaverse Workshop 2023 (code is available at https://github.com/dakshitagrawal/NoVA) |
| Document Type: |
Working Paper |
| Access URL: |
http://arxiv.org/abs/2308.12560 |
| Accession Number: |
edsarx.2308.12560 |
| Database: |
arXiv |
