Video Rescaling Networks with Joint Optimization Strategies for Downscaling and Upscaling

TL;DR

This paper introduces two novel neural network approaches for joint video downscaling and upscaling, leveraging temporal information and group processing to improve quality over existing image-based methods.

Contribution

It presents the first joint optimization framework for video downscaling and upscaling using invertible neural networks with temporal and group-based strategies.

Findings

Outperforms image-based invertible models in quality.

Achieves significantly better upscaling results than non-joint methods.

Introduces two new models: LSTM-VRN and MIMO-VRN.

Abstract

This paper addresses the video rescaling task, which arises from the needs of adapting the video spatial resolution to suit individual viewing devices. We aim to jointly optimize video downscaling and upscaling as a combined task. Most recent studies focus on image-based solutions, which do not consider temporal information. We present two joint optimization approaches based on invertible neural networks with coupling layers. Our Long Short-Term Memory Video Rescaling Network (LSTM-VRN) leverages temporal information in the low-resolution video to form an explicit prediction of the missing high-frequency information for upscaling. Our Multi-input Multi-output Video Rescaling Network (MIMO-VRN) proposes a new strategy for downscaling and upscaling a group of video frames simultaneously. Not only do they outperform the image-based invertible model in terms of quantitative and qualitative results, but also show much improved upscaling quality than the video rescaling methods without joint optimization. To our best knowledge, this work is the first attempt at the joint optimization of video downscaling and upscaling.