HyperAIHyperAI

Command Palette

Search for a command to run...

3 months ago

ACCURATE METHOD OF TEMPORAL-SHIFT ESTIMATION FOR 3D VIDEO

{Dmitriy Vatolin Aleksandr Ploshkin}

Abstract

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.

Benchmarks

BenchmarkMethodologyMetrics
video-alignment-on-msu-video-alignment-andVQMT3D
Accuracy w/ 3 frames error (Hard): 0
Accuracy w/ 3 frames error (Light): 0.3219
Accuracy w/ 3 frames error (Medium color): 0.3255
Accuracy w/ 3 frames error (Medium geometric): 0.2625

Build AI with AI

From idea to launch — accelerate your AI development with free AI co-coding, out-of-the-box environment and best price of GPUs.

AI Co-coding
Ready-to-use GPUs
Best Pricing
Get Started

Hyper Newsletters

Subscribe to our latest updates
We will deliver the latest updates of the week to your inbox at nine o'clock every Monday morning
Powered by MailChimp
ACCURATE METHOD OF TEMPORAL-SHIFT ESTIMATION FOR 3D VIDEO | Papers | HyperAI