NOVA: NOvel View Augmentation for Neural Composition of Dynamic Objects
This addresses neural composition of dynamic objects for computer graphics and vision applications, representing an incremental improvement over prior work.
The paper tackles the problem of inserting multiple dynamic objects into 3D scenes using NeRFs, achieving significant reduction in blending artifacts at novel views and times while maintaining comparable PSNR without requiring additional ground truth like optical flow.
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.