Name
Abstract | ||
|---|---|---|
With the recent advent of methods that allow for real-time computation, dense 3D flows have become a viable basis for fast camera motion estimation. Most importantly, dense flows are more robust than the sparse feature matching techniques used by existing 3D stabilization methods, able to better handle large camera displacements and occlusions similar to those often found in consumer videos. Here we introduce a framework for 3D video stabilization that relies on dense scene flow alone. The foundation of this approach is a novel camera motion model that allows for real-world camera poses to be recovered directly from 3D motion fields. Moreover, this model can be extended to describe certain types of non-rigid artifacts that are commonly found in videos, such as those resulting from zooms. This framework gives rise to several robust regimes that produce high-quality stabilization of the kind achieved by prior full 3D methods while avoiding the fragility typically present in feature-based approaches. As an added benefit, our framework is fast: the simplicity of our motion model and efficient flow calculations combine to enable stabilization at a high frame rate. |
Year | Venue | Field |
|---|---|---|
2019 | arXiv: Computer Vision and Pattern Recognition | Computer vision,Kinematics,Pattern recognition,Computer science,Flow (psychology),Image stabilization,Fragility,Feature matching,Artificial intelligence,Frame rate,Motion estimation,Computation |
DocType | Volume | Citations |
Journal | abs/1903.09073 | 0 |
PageRank | References | Authors |
0.34 | 0 | 5 |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Thomas W. Mitchel | 1 | 1 | 2.05 |
| Christian Wülker | 2 | 0 | 0.34 |
| Jin Seob Kim | 3 | 0 | 0.34 |
| Sipu Ruan | 4 | 1 | 2.73 |
| Gregory Chirikjian | 5 | 1087 | 124.75 |