NOVA: NOvel View Augmentation for Neural Composition of Dynamic Objects
arXiv:2308.12560
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.
Accepted for publication in ICCV Computer Vision for Metaverse Workshop 2023 (code is available at https://github.com/dakshitagrawal/NoVA)