Learned Video Codec with Enriched Reconstruction for CLIC P-frame Coding
This work addresses the problem of efficient video compression for the CLIC P-frame Challenge, providing an incremental improvement for researchers and practitioners in video coding.
This paper proposes a learning-based video codec for P-frame coding, specifically for the CLIC 2020 P-frame Challenge. The codec utilizes a Refine-Net for residual and motion vector coding and a hierarchical, attention-based ME-Net for motion estimation, achieving competitive performance against top performers in the challenge.
This paper proposes a learning-based video codec, specifically used for Challenge on Learned Image Compression (CLIC, CVPRWorkshop) 2020 P-frame coding. More specifically, we designed a compressor network with Refine-Net for coding residual signals and motion vectors. Also, for motion estimation, we introduced a hierarchical, attention-based ME-Net. To verify our design, we conducted an extensive ablation study on our modules and different input formats. Our video codec demonstrates its performance by using the perfect reference frame at the decoder side specified by the CLIC P-frame Challenge. The experimental result shows that our proposed codec is very competitive with the Challenge top performers in terms of quality metrics.