B-CANF：基于条件增广归一化流的B帧自适应编码
B-CANF: Adaptive B-frame Coding with Conditional Augmented Normalizing Flows
AI总结：
本文提出B-CANF框架，利用条件增广归一化流进行B帧编码，引入帧类型自适应编码优化比特分配，并通过B*-帧重用B帧编解码器模拟P帧编码，在常用数据集上实现了最先进的压缩性能。
摘要：
过去几年中，基于学习的视频压缩已成为一个活跃的研究领域。然而，大多数工作集中在P帧编码上。基于学习的B帧编码研究尚不充分且更具挑战性。本文提出了一种新颖的B帧编码框架，称为B-CANF，利用条件增广归一化流进行B帧编码。B-CANF还包含两个新元素：帧类型自适应编码和B*-帧。我们的帧类型自适应编码通过根据B帧类型动态调整特征分布，为分层B帧编码学习更好的比特分配。我们的B*-帧允许在指定图像组（GOP）结构时具有更大的灵活性，它通过重用B帧编解码器来模拟P帧编码，而无需额外的独立P帧编解码器。在常用数据集上，与其他基于学习的B帧编解码器相比，B-CANF实现了最先进的压缩性能，并且在随机访问配置下，其BD-rate结果在PSNR方面与HM-16.23相当。在不同的GOP结构上评估时，我们的B*-帧实现了与额外使用独立P帧编解码器相似的性能。
英文摘要：
Over the past few years, learning-based video compression has become an active research area. However, most works focus on P-frame coding. Learned B-frame coding is under-explored and more challenging. This work introduces a novel B-frame coding framework, termed B-CANF, that exploits conditional augmented normalizing flows for B-frame coding. B-CANF additionally features two novel elements: frame-type adaptive coding and B*-frames. Our frame-type adaptive coding learns better bit allocation for hierarchical B-frame coding by dynamically adapting the feature distributions according to the B-frame type. Our B*-frames allow greater flexibility in specifying the group-of-pictures (GOP) structure by reusing the B-frame codec to mimic P-frame coding, without the need for an additional, separate P-frame codec. On commonly used datasets, B-CANF achieves the state-of-the-art compression performance as compared to the other learned B-frame codecs and shows comparable BD-rate results to HM-16.23 under the random access configuration in terms of PSNR. When evaluated on different GOP structures, our B*-frames achieve similar performance to the additional use of a separate P-frame codec.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
