AIM 2019 Challenge on Video Temporal Super-Resolution: Methods and Results

TL;DR

This paper reviews the AIM 2019 challenge on video temporal super-resolution, highlighting innovative methods and state-of-the-art results in increasing video frame rates from low-frame-rate videos.

Contribution

It presents the first AIM challenge on video temporal super-resolution, showcasing diverse solutions and benchmarking their performance on a new dataset.

Findings

Winning methods achieve state-of-the-art performance

62 participants registered, 8 teams competed

The challenge advances the field of video frame interpolation

Abstract

Videos contain various types and strengths of motions that may look unnaturally discontinuous in time when the recorded frame rate is low. This paper reviews the first AIM challenge on video temporal super-resolution (frame interpolation) with a focus on the proposed solutions and results. From low-frame-rate (15 fps) video sequences, the challenge participants are asked to submit higher-framerate (60 fps) video sequences by estimating temporally intermediate frames. We employ the REDS VTSR dataset derived from diverse videos captured in a hand-held camera for training and evaluation purposes. The competition had 62 registered participants, and a total of 8 teams competed in the final testing phase. The challenge winning methods achieve the state-of-the-art in video temporal superresolution.