Texture-aware Video Frame Interpolation

TL;DR

This paper investigates how different video textures affect frame interpolation performance and proposes a framework with specialized models for static, dynamic continuous, and dynamic discrete textures, improving accuracy.

Contribution

It introduces a novel approach of training separate interpolation models for different texture classes, enhancing interpolation quality over generic models.

Findings

Models trained with texture-specific adaptation outperform generic models.

Achieved an average 0.3dB PSNR improvement on test data.

Texture-aware models better capture diverse motion characteristics.

Abstract

Temporal interpolation has the potential to be a powerful tool for video compression. Existing methods for frame interpolation do not discriminate between video textures and generally invoke a single general model capable of interpolating a wide range of video content. However, past work on video texture analysis and synthesis has shown that different textures exhibit vastly different motion characteristics and they can be divided into three classes (static, dynamic continuous and dynamic discrete). In this work, we study the impact of video textures on video frame interpolation, and propose a novel framework where, given an interpolation algorithm, separate models are trained on different textures. Our study shows that video texture has significant impact on the performance of frame interpolation models and it is beneficial to have separate models specifically adapted to these texture classes, instead of training a single model that tries to learn generic motion. Our results demonstrate that models fine-tuned using our framework achieve, on average, a 0.3dB gain in PSNR on the test set used.