Neural video compression (NVC) has made significant progress in recent years, while neural B-frame video compression (NBVC) remains underexplored compared to P-frame compression. NBVC can adopt bi-directional reference frames for better compression performance. However, NBVC's hierarchical coding may complicate continuous temporal prediction, especially at some hierarchical levels with a large frame span, which could cause the contribution of the two reference frames to be unbalanced. To optimize reference information utilization, we propose a novel NBVC method, termed Bi-directional Reference Harmonization Video Compression (BRHVC), with the proposed Bi-directional Motion Converge (BMC) and Bi-directional Contextual Fusion (BCF).

Implicit Neural Representations (INRs) have previously been used to represent and compress image and video content, demonstrating relatively high decoding speed compared to other methods.

Our approach builds upon variational autoencoder (V AE) models for sequential data and combines them with recent work on neural image compression.

Dear Reviewers, we thank you for taking the time to provide valuable feedback. Below we address the main issues raised. Its performance depends on our ability to predict the distribution over future frames with low entropy. We will emphasize these aspects more in a revised version. RNNs to model dynamics in the latent space.

Giventheir remarkable representational capacity [1], we choose deep neural networks as the function in our work.