Efficient Bitrate Ladder Construction using Transfer Learning and Spatio-Temporal Features

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Falahati, Ali, Safavi, Mohammad Karim, Elahi, Ardavan, Pakdaman, Farhad, Gabbouj, Moncef
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914757404000256
author Falahati, Ali
Safavi, Mohammad Karim
Elahi, Ardavan
Pakdaman, Farhad
Gabbouj, Moncef
author_facet Falahati, Ali
Safavi, Mohammad Karim
Elahi, Ardavan
Pakdaman, Farhad
Gabbouj, Moncef
contents Providing high-quality video with efficient bitrate is a main challenge in video industry. The traditional one-size-fits-all scheme for bitrate ladders is inefficient and reaching the best content-aware decision computationally impractical due to extensive encodings required. To mitigate this, we propose a bitrate and complexity efficient bitrate ladder prediction method using transfer learning and spatio-temporal features. We propose: (1) using feature maps from well-known pre-trained DNNs to predict rate-quality behavior with limited training data; and (2) improving highest quality rung efficiency by predicting minimum bitrate for top quality and using it for the top rung. The method tested on 102 video scenes demonstrates 94.1% reduction in complexity versus brute-force at 1.71% BD-Rate expense. Additionally, transfer learning was thoroughly studied through four networks and ablation studies.
format Preprint
id arxiv_https___arxiv_org_abs_2401_03195
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Efficient Bitrate Ladder Construction using Transfer Learning and Spatio-Temporal Features
Falahati, Ali
Safavi, Mohammad Karim
Elahi, Ardavan
Pakdaman, Farhad
Gabbouj, Moncef
Multimedia
Computer Vision and Pattern Recognition
Machine Learning
I.4.2
Providing high-quality video with efficient bitrate is a main challenge in video industry. The traditional one-size-fits-all scheme for bitrate ladders is inefficient and reaching the best content-aware decision computationally impractical due to extensive encodings required. To mitigate this, we propose a bitrate and complexity efficient bitrate ladder prediction method using transfer learning and spatio-temporal features. We propose: (1) using feature maps from well-known pre-trained DNNs to predict rate-quality behavior with limited training data; and (2) improving highest quality rung efficiency by predicting minimum bitrate for top quality and using it for the top rung. The method tested on 102 video scenes demonstrates 94.1% reduction in complexity versus brute-force at 1.71% BD-Rate expense. Additionally, transfer learning was thoroughly studied through four networks and ablation studies.
title Efficient Bitrate Ladder Construction using Transfer Learning and Spatio-Temporal Features
topic Multimedia
Computer Vision and Pattern Recognition
Machine Learning
I.4.2
url https://arxiv.org/abs/2401.03195