Explorando a eficiência de compressão e qualidade de vídeo: um estudo sobre Codecs de vídeo baseados em Deep Learning

Advancements in video streaming technology have revolutionized the way content Multimedia is consumed, becoming an essential component in the distribution of information and entertainment. Transmission efficiency and video quality are only critical aspects, especially in a scenario where the demand...

Descripción completa

Detalles Bibliográficos
Autor: Nascimento, Mairon Felipe Barreto
Tipo de recurso: tesis de maestría
Estado:Versión publicada
Fecha de publicación:2024
País:Brasil
Institución:Universidade Federal de Sergipe (UFS)
Repositorio:Repositório Institucional da UFS
Idioma:portugués
OAI Identifier:oai:oai:ri.ufs.br:repo_01:riufs/22466
Acceso en línea:https://ri.ufs.br/jspui/handle/riufs/22466
Access Level:acceso abierto
Palabra clave:Codificador e Decodificador (CODEC)
Deep Learning
Compressão de vídeo
Streaming
Vídeo Compression
Descripción
Sumario:Advancements in video streaming technology have revolutionized the way content Multimedia is consumed, becoming an essential component in the distribution of information and entertainment. Transmission efficiency and video quality are only critical aspects, especially in a scenario where the demand for high-resolution content is constant growth To meet these needs, video encoders/decoders (Codecs) and Efficient compression techniques are essential. Traditionally, Codecs like H.264 and H.265 played a key role in video compression, but it was also learned profound brought new possibilities and challenges to this field. This work aimed to investigate and compare innovative solutions that can be applied to improve efficiency compression and video quality in real-time streaming scenarios using or potential of deep learning techniques. The study included analysis of publications identify the proposed contributions and their limitations within the paradigm Codec based on Deep Learning, in relation to traditional approaches to optimization CODECs with the aim of reducing the amount of bandwidth used.