Adaptive and Asymmetrical Blending for Bi-Directional Inter Prediction of Various Visual Contents in Video Coding

Versatile Video Coding (VVC) standard adopts the geometric partition mode (GPM) to enhance inter prediction by supporting non-rectangular partitions in a block. The GPM improves coding efficiency by effectively handling arbitrary partitions caused by the motion of irregularly shaped objects in a scene. However, the blending process of GPM prediction suffers from limitations, primarily because the equal treatment given to blending ranges for predictors, disregarding the unique visual characteristics of diverse video content, leads to suboptimal performance. This study presents a comprehensive approach using adaptive and asymmetrical blending for the GPM (AAGPM) to enhance the performance of the blending technique by introducing two novel blending methods: a difference-based adaptive blending method and an implicitly asymmetrical blending mechanism. The difference-based method enhances the prediction accuracy by adaptively assigning more relevant blending weights to the dominant predictors. In addition, the asymmetrical mechanism adaptively adjusts the blending ranges without additional signaling by analyzing the local and global characteristics based on the reconstructed signal and predictors. These methods enable adaptive and content-aware adjustment of blending matrices, improve edge quality by preserving intrinsic edges, and prevent over-smoothing in complex sequences across diverse video content, including camera-captured, computer-generated, and mixed content. The proposed algorithm is implemented using the VVC reference software, VTM-18.0, and enhanced compression model (ECM)-6.0, respectively. Experimental results demonstrate that the algorithm achieves a Bjøntegaard Delta bitrate (BD-rate) savings of 0.86% and 0.50% for low-delay B and random-access configurations, respectively, compared to VVC. It also shows improved compression performance compared to ECM.