ODVISTA: An Omnidirectional Video Dataset for Super-Resolution and Quality Enhancement Tasks

Omnidirectional or 360-degree video is being increasingly deployed, largely due to the latest advancements in immersive virtual reality (VR) and extended reality (XR) technology. However, the adoption of these videos in streaming encounters challenges related to bandwidth and latency, particularly in mobility conditions such as with unmanned aerial vehicles (UAVs). Adaptive resolution and compression aim to preserve quality while maintaining low latency under these constraints, yet downscaling and encoding can still degrade quality and introduce artifacts. Machine learning (ML)-based super-resolution (SR) and quality enhancement techniques offer a promising solution by enhancing detail recovery and reducing compression artifacts. However, current publicly available 360-degree video SR datasets lack compression artifacts, which limit research in this field. To bridge this gap, this paper introduces omnidirectional video streaming dataset (ODVista), which comprises 200 high-resolution and high-quality videos downscaled and encoded at four bitrate ranges using the high-efficiency video coding (HEVC)/H.265 standard. Evaluations show that the dataset not only features a wide variety of scenes but also spans different levels of content complexity, which is crucial for robust solutions that perform well in real-world scenarios and generalize across diverse visual environments. Additionally, we evaluate the performance, considering both quality enhancement and runtime, of two handcrafted and two ML-based SR models on the validation and testing sets of ODVista. Dataset URL: https://github.com/Omnidirectional-video-group/ODVista

1. Introduction

Advancements in immersive video technologies have paved the way for users to engage in a virtual environment that mirrors real-life scenarios, thereby enhancing user engagement and a sense of belonging in a digital space. Various visual media formats, including omnidirectional video (ODV), volumetric videos, and light fields, are common and effective methods for facilitating an immersive viewing experience. In particular, ODV, also known as 360-degree video, has gained widespread popularity due to the availability of acquisition and display devices, as well as standardization efforts to ensure interoperability. However, the adoption of these videos in streaming encounters challenges related to bandwidth and latency, particularly in mobility conditions such as unmanned aerial vehicles (UAVs). Adaptive resolution and compression aim to maintain quality while minimizing latency in such scenarios. Nevertheless, the process of downscaling and encoding may result in quality degradation and the introduction of compression artifacts.