用掩码扩散模型实现视频无损压缩，利用帧间冗余提升效率。
NeuralLVC: Neural Lossless Video Compression via Masked Diffusion with Temporal Conditioning
- 基于掩码扩散与I/P帧架构，通过参考帧嵌入捕捉时间冗余。
- 在9个Xiph CIF序列上优于H.264/H.265无损编码，重建完全精确。
- 仅增加1.3%参数，支持可调速度-压缩率权衡，适合高效无损视频场景。
尽管神经网络无损图像压缩已取得显著进展，但神经网络下的无损视频压缩仍鲜有研究。我们提出NeuralLVC，一种结合掩码扩散与I/P帧结构的神经无损视频编解码器，以利用时间冗余。I帧模型通过双射线性标记化压缩单帧，保证像素级精确重建；P帧模型则对相邻帧间的差异进行压缩，通过轻量级参考嵌入条件化，仅增加1.3%可训练参数。分组解码支持可控的速度-压缩率权衡。该编解码器在输入域内为无损：对视频，精确重构YUV420各平面；对图像评估，RGB通道完全还原。在9个Xiph CIF序列上的实验表明，NeuralLVC显著优于H.264和H.265无损模式。通过算术编码的端到端编解码测试验证了精确重建。结果表明，带有时间条件化的掩码扩散是神经无损视频压缩的有前景方向。
原文摘要 · Abstract (English)
While neural lossless image compression has advanced significantly with learned entropy models, lossless video compression remains largely unexplored in the neural setting. We present NeuralLVC, a neural lossless video codec that combines masked diffusion with an I/P-frame architecture for exploiting temporal redundancy. Our I-frame model compresses individual frames using bijective linear tokenization that guarantees exact pixel reconstruction. The P-frame model compresses temporal differences between consecutive frames, conditioned on the previous decoded frame via a lightweight reference embedding that adds only 1.3% trainable parameters. Group-wise decoding enables controllable speed-compression trade-offs. Our codec is lossless in the input domain: for video, it reconstructs YUV420 planes exactly; for image evaluation, RGB channels are reconstructed exactly. Experiments on 9 Xiph CIF sequences show that NeuralLVC outperforms H.264 and H.265 lossless by a significant margin. We verify exact reconstruction through end-to-end encode-decode testing with arithmetic coding. These results suggest that masked diffusion with temporal conditioning is a promising direction for neural lossless video compression.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。