Reading: DeepQTMT — A Deep Learning Approach for Fast QTMT-based CU Partition of Intra-mode VVC…

Original article was published on Deep Learning on Medium


As shown above, ternary-tree split CUs, i.e., modes 4 and 5, account for less than 15% for all CU sizes, while non-splitting CUs, i.e., mode 0, are predominant for most CU sizes. Thus, the multi-stage CU partition problem is more sophisticated than a typical image classification problem with only one output and balanced classes.