Scale-aware Insertion of Virtual Objects in Monocular Videos
This work is significant for computer graphics and augmented reality applications, enabling more realistic virtual object insertion for users working with monocular video.
This paper addresses the challenge of inserting virtual objects into monocular videos with correct scaling by estimating the global scale of objects using a Bayesian approach that incorporates size priors. The method outperforms state-of-the-art scale estimation techniques, demonstrating improved validity and robustness across various video scenes.
In this paper, we propose a scale-aware method for inserting virtual objects with proper sizes into monocular videos. To tackle the scale ambiguity problem of geometry recovery from monocular videos, we estimate the global scale objects in a video with a Bayesian approach incorporating the size priors of objects, where the scene objects sizes should strictly conform to the same global scale and the possibilities of global scales are maximized according to the size distribution of object categories. To do so, we propose a dataset of sizes of object categories: Metric-Tree, a hierarchical representation of sizes of more than 900 object categories with the corresponding images. To handle the incompleteness of objects recovered from videos, we propose a novel scale estimation method that extracts plausible dimensions of objects for scale optimization. Experiments have shown that our method for scale estimation performs better than the state-of-the-art methods, and has considerable validity and robustness for different video scenes. Metric-Tree has been made available at: https://metric-tree.github.io