ACCURATE METHOD OF TEMPORAL-SHIFT ESTIMATION FOR 3D VIDEO
Video synchronization is a fundamental computer-vision task that is necessary for a wide range of applications. A 3D video involves two streams, which show the scene from different angles concurrently, but many cases exhibit desynchronization between them. This paper investigates the problem of synchronizing the left and right stereoscopic views. We assume the temporal shift (time difference) and geometric distortion between the two streams are constant throughout each scene. We propose a temporal-shift estimation method with subframe accuracy based on a block-matching algorithm.
PDF Abstract
Results from the Paper
| Task | Dataset | Model | Metric Name | Metric Value | Global Rank | Benchmark |
|---|---|---|---|---|---|---|
| Video Alignment | MSU Video Alignment and Retrieval Benchmark Suite | VQMT3D | Accuracy w/ 3 frames error (Light) | 0.3219 | # 1 | |
| Accuracy w/ 3 frames error (Medium geometric) | 0.2625 | # 2 | ||||
| Accuracy w/ 3 frames error (Medium color) | 0.3255 | # 1 | ||||
| Accuracy w/ 3 frames error (Hard) | 0 | # 4 |
Methods
No methods listed for this paper. Add
relevant methods here
