Texture-aware Video Frame Interpolation
This work addresses video compression by improving interpolation accuracy for specific textures, though it is incremental as it builds on existing texture classification and interpolation methods.
The paper tackled the problem of video frame interpolation by proposing a texture-aware framework that trains separate models for different video texture classes, achieving an average 0.3dB PSNR gain on the test set.
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.