DynIBaR: Neural Dynamic Image-Based Rendering
Authors:
Preprint
Abstract
We address the problem of synthesizing novel views from a monocular video depicting a complex dynamic scene. State-of-the-art methods based on temporally varying Neural Radiance Fields (aka dynamic NeRFs) have shown impressive results on this task. However, for long videos with complex object motions and uncontrolled camera trajectories, these methods can produce blurry or inaccurate renderings, hampering their use in real-world applications. Instead of encoding the entire dynamic scene within the weights of an MLP, we present a new approach that addresses these limitations by adopting a volumetric image-based rendering framework that synthesizes new viewpoints by aggregating features from nearby views in a scene-motion-aware manner. Our system retains the advantages of prior methods in its ability to model complex scenes and view-dependent effects, but also enables synthesizing photo-realistic novel views from long videos featuring complex scene dynamics with unconstrained camera trajectories. We demonstrate significant improvements over state-of-the-art methods on dynamic scene datasets, and also apply our approach to in-the-wild videos with challenging camera and object motion, where prior methods fail to produce high-quality renderings. Our project webpage is at dynibar.github.io.Keywords
All Related Versions
This publication has 13 references indexed in Scilit:
- Neural Rays for Occlusion-aware Image-based Rendering2022
- Layered neural rendering for retiming people in videoACM Transactions on Graphics, 2020
- Consistent video depth estimationACM Transactions on Graphics, 2020
- Immersive light field video with a layered mesh representationACM Transactions on Graphics, 2020
- Deep blending for free-viewpoint image-based renderingACM Transactions on Graphics, 2018
- Soft 3D reconstruction for view synthesisACM Transactions on Graphics, 2017
- Learning-based view synthesis for light field camerasACM Transactions on Graphics, 2016
- Scalable inside-out image-based renderingACM Transactions on Graphics, 2016
- Real-time non-rigid reconstruction using an RGB-D cameraACM Transactions on Graphics, 2014
- Virtualized reality: constructing virtual worlds from real scenesIEEE MultiMedia, 1997