Reparo: Loss-Resilient Generative Codec for Video Conferencing

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Li, Tianhong, Sivaraman, Vibhaalakshmi, Karimi, Pantea, Fan, Lijie, Alizadeh, Mohammad, Katabi, Dina
Formato: Preprint
Publicado: 2023
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866913532541403136
author Li, Tianhong
Sivaraman, Vibhaalakshmi
Karimi, Pantea
Fan, Lijie
Alizadeh, Mohammad
Katabi, Dina
author_facet Li, Tianhong
Sivaraman, Vibhaalakshmi
Karimi, Pantea
Fan, Lijie
Alizadeh, Mohammad
Katabi, Dina
contents Packet loss during video conferencing often results in poor quality and video freezing. Retransmitting lost packets is often impractical due to the need for real-time playback, and using Forward Error Correction (FEC) for packet recovery is challenging due to the unpredictable and bursty nature of Internet losses. Excessive redundancy leads to inefficiency and wasted bandwidth, while insufficient redundancy results in undecodable frames, causing video freezes and quality degradation in subsequent frames. We introduce Reparo -- a loss-resilient video conferencing framework based on generative deep learning models to address these issues. Our approach generates missing information when a frame or part of a frame is lost. This generation is conditioned on the data received thus far, considering the model's understanding of how people and objects appear and interact within the visual realm. Experimental results, using publicly available video conferencing datasets, demonstrate that Reparo outperforms state-of-the-art FEC-based video conferencing solutions in terms of both video quality (measured through PSNR, SSIM, and LPIPS) and the occurrence of video freezes.
format Preprint
id arxiv_https___arxiv_org_abs_2305_14135
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Reparo: Loss-Resilient Generative Codec for Video Conferencing
Li, Tianhong
Sivaraman, Vibhaalakshmi
Karimi, Pantea
Fan, Lijie
Alizadeh, Mohammad
Katabi, Dina
Networking and Internet Architecture
Computer Vision and Pattern Recognition
Packet loss during video conferencing often results in poor quality and video freezing. Retransmitting lost packets is often impractical due to the need for real-time playback, and using Forward Error Correction (FEC) for packet recovery is challenging due to the unpredictable and bursty nature of Internet losses. Excessive redundancy leads to inefficiency and wasted bandwidth, while insufficient redundancy results in undecodable frames, causing video freezes and quality degradation in subsequent frames. We introduce Reparo -- a loss-resilient video conferencing framework based on generative deep learning models to address these issues. Our approach generates missing information when a frame or part of a frame is lost. This generation is conditioned on the data received thus far, considering the model's understanding of how people and objects appear and interact within the visual realm. Experimental results, using publicly available video conferencing datasets, demonstrate that Reparo outperforms state-of-the-art FEC-based video conferencing solutions in terms of both video quality (measured through PSNR, SSIM, and LPIPS) and the occurrence of video freezes.
title Reparo: Loss-Resilient Generative Codec for Video Conferencing
topic Networking and Internet Architecture
Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2305.14135