Texture Segmentation Based Video Compression Using Convolutional Neural Networks
This work addresses the need for more efficient video codecs to support growing web-based video consumption, representing an incremental improvement in compression techniques.
The paper tackled the problem of improving video compression efficiency by proposing a model-based approach that uses texture analysis/synthesis with convolutional neural networks to reconstruct texture regions in videos, achieving an increase in coding efficiency while maintaining satisfactory visual quality.
There has been a growing interest in using different approaches to improve the coding efficiency of modern video codec in recent years as demand for web-based video consumption increases. In this paper, we propose a model-based approach that uses texture analysis/synthesis to reconstruct blocks in texture regions of a video to achieve potential coding gains using the AV1 codec developed by the Alliance for Open Media (AOM). The proposed method uses convolutional neural networks to extract texture regions in a frame, which are then reconstructed using a global motion model. Our preliminary results show an increase in coding efficiency while maintaining satisfactory visual quality.