研究人员开发了新的神经视频压缩方法，重点是提高效率和质量。一种方法，可变形时间对齐和差分感知融合，通过生成互补的时间上下文和自适应地选择可靠信息来解决运动估计和对齐错误的问题。另一种方法 LRConv-NeRV 通过用结构化低秩可分离卷积替换密集卷积层来降低计算复杂度和模型大小，在质量损失最小的情况下实现了显著的效率提升。此外，还提出了一种可扩展的神经视频编解码器 (S-NVRC)，用于从单个比特流支持细粒度的比特率和解码复杂度可扩展性，其性能优于现有的可扩展和不可扩展编解码器。
AI
arXiv:2609.03520v1 Announce Type: cross Abstract: In conditional coding-based neural video compression, the quality of temporal context directly affects compression per- formance. Existing methods mostly construct context from prop- agated reference features, but they are vulnera…
arXiv:2603.18261v2 Announce Type: replace-cross Abstract: Neural Representations for Videos (NeRV) encode entire video sequences within neural network parameters, offering an alternative paradigm to conventional video codecs. However, the convolutional decoder of NeRV remains com…
Overfitted codecs have demonstrated promising performance for image and video compression. In particular, for image compression, the Cool-chic family of models has shown competitive performance against scene-agnostic models, with orders of magnitude lower decoding complexity at t…
arXiv cs.CV
TIER_1Italiano(IT)·Tianhao Peng, Ho Man Kwan, Fan Zhang, Shan Liu, David Bull·
arXiv:2609.04273v1 Announce Type: cross Abstract: Scalable video coding (SVC) encodes a video into a layered bitstream consisting of a base layer and one or multiple enhancement layers, enabling decoding at different bitrate/quality/resolution operating points to accommodate dive…
arXiv cs.CV
TIER_1Italiano(IT)·Tianhao Peng, Ho Man Kwan, Fan Zhang, Shan Liu, David Bull·
arXiv:2609.04274v1 Announce Type: cross Abstract: Overfitted codecs have demonstrated promising performance for image and video compression. In particular, for image compression, the Cool-chic family of models has shown competitive performance against scene-agnostic models, with …
