BiCRVC：一种基于耦合表示编码的高效双向神经视频压缩框架
BiCRVC: An Efficient Bidirectional Neural Video Compression Framework via Coupled Representation Coding
AI总结：
BiCRVC是一种基于耦合表示编码的高效双向神经视频压缩框架，通过多候选运动估计等技术解决双向NVC的技术挑战，压缩性能更优且1080p解码速度约为近期BVC的30倍。
AI中文摘要：
神经视频压缩（NVC）已取得优异的压缩性能，但实用的随机接入编码仍面临两项技术挑战：现有双向神经视频压缩（BVC）通常需要代价高昂的运动优先解码，且在长距离双向预测下难以实现可靠的运动估计。为解决这些问题，本文提出BiCRVC，一种基于耦合表示编码的高效双向神经视频压缩框架。BiCRVC未采用两个独立编解码器分别编码运动与帧信息，而是将运动表示和当前帧的隐特征转换为统一的隐特征以进行熵编码。该设计使运动和帧信息可通过一个统一编解码器从同一比特流中解码，同时仍能重构用于帧解码的运动对齐上下文。为提升运动估计精度，本文引入多候选运动估计（MCME），其结合多尺度运动估计与并行累积运动估计，以更好地处理多样且长距离的运动。为降低运动编码开销，本文进一步提出双向运动特征传播（BMFP），在编码器和解码器处复用先前解码的运动特征作为时间先验，用于条件运动编码。此外，采用耦合失真训练与随机GOP结构训练，以促进运动-帧联合编码并提升对分层随机接入结构的适应性。实验表明，BiCRVC的压缩性能优于现有最优BVC，且其1080p解码速度约为近期BVC的30倍。
英文摘要：
Neural video compression (NVC) has achieved strong compression performance, but practical random-access coding still faces two technical challenges: existing bidirectional NVCs (BVCs) usually require costly motion-first decoding, and reliable motion estimation is difficult under long-range bidirectional prediction. To address these issues, we present BiCRVC, an efficient bidirectional neural video compression framework based on coupled representation coding. Instead of coding motion and frame information with two separate codecs, BiCRVC transforms the motion representation and the current-frame latent into a unified latent representation for entropy coding. This design enables motion and frame information to be decoded from the same bitstream with one unified codec, while still reconstructing motion-aligned contexts for frame decoding. To improve motion accuracy, we introduce multi-candidate motion estimation (MCME), which combines multi-scale motion estimation and parallel accumulated motion estimation to better handle diverse and long-range motions. To reduce motion coding overhead, we further propose bidirectional motion feature propagation (BMFP), which reuses previously decoded motion features at both the encoder and decoder as temporal priors for conditional motion coding. In addition, coupled distortion training and random GOP structure training are used to encourage joint motion-frame coding and improve adaptation to hierarchical random-access structures. Experiments show that BiCRVC achieves better compression performance than state-of-the-art BVCs while providing about 30 times faster 1080p decoding than recent BVCs.
