We propose Deep3D Stabilizer, a novel 3D depth-based learning method for video stabilization. Our approach requires no data for pre-training but stabilizes the input video via 3D reconstruction directly. The rectification stage incorporates the 3D scene depth and camera motion to smooth the camera trajectory and synthesize the stabilized video. Unlike most one-size-fits-all learning-based methods, our smoothing algorithm allows users to manipulate the stability of a video efficiently.
@InProceedings{Lee_2021_CVPR
author = {Lee, Yao-Chih and Tseng, Kuan-Wei and Chen, Yu-Ta and Chen, Chien-Cheng and Chen, Chu-Song and Hung, Yi-Ping},title = {3D Video Stabilization with Depth Estimation by CNN-based Optimization},booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},month = {June},year = {2021},pages = {10621-10630}}
Acknowledgment
This work was partially supported by MediaTek Inc., and Ministry of Science and Technology in Taiwan.