BoostMVSNeRFs: Boosting MVS-based NeRFs to Generalizable View Synthesis in Large-scale Scenes.
Chih-Hai SuChih-Yao HuShr-Ruei TsaiJie-Ying LeeChin-Yang LinYu-Lun LiuPublished in: CoRR (2024)
Keyphrases
- object tracking
- video surveillance
- view synthesis
- multiple cameras
- scene geometry
- camera views
- mean shift
- depth map
- multi view
- scene understanding
- intermediate views
- d scene
- view interpolation
- dynamic scenes
- real scenes
- motion vectors
- virtual view
- photorealistic
- complex scenes
- multiview video
- camera calibration
- ground truth