通过潜在扩散模型灵活调节图像压缩的失真与感知质量平衡。
Controllable Distortion-Perception Tradeoff Through Latent Diffusion for Neural Image Compression
- 在解码器引入可插拔的潜在扩散模块，提升感知质量或降低失真。
- 在不损失原始编码能力前提下，实现超过150%的LPIPS-BDRate提升。
- 无需重新训练，推理时自由调节失真与感知权重，适合实际应用。
神经图像压缩常面临率、失真和感知之间的权衡难题。现有方法通常侧重于像素级保真度或感知指标优化，而本文提出一种新方法，针对固定神经图像编解码器，同时兼顾两者。具体而言，在解码器侧引入一个即插即用模块，利用潜在扩散过程对解码特征进行转换，可在不改变原编码器的情况下，增强低失真或高感知质量表现。该方法通过融合原始与变换后的特征，无需额外训练即可在推理阶段灵活调整失真与感知的平衡。大量实验表明，该方法显著提升了预训练编解码器的性能，扩展了可调的失真-感知范围，同时保持原有压缩能力。例如，可在不超过1 dB PSNR损失的前提下，实现超过150%的LPIPS-BDRate提升。
原文摘要 · Abstract (English)
Neural image compression often faces a challenging trade-off among rate, distortion and perception. While most existing methods typically focus on either achieving high pixel-level fidelity or optimizing for perceptual metrics, we propose a novel approach that simultaneously addresses both aspects for a fixed neural image codec. Specifically, we introduce a plug-and-play module at the decoder side that leverages a latent diffusion process to transform the decoded features, enhancing either low distortion or high perceptual quality without altering the original image compression codec. Our approach facilitates fusion of original and transformed features without additional training, enabling users to flexibly adjust the balance between distortion and perception during inference. Extensive experimental results demonstrate that our method significantly enhances the pretrained codecs with a wide, adjustable distortion-perception range while maintaining their original compression capabilities. For instance, we can achieve more than 150% improvement in LPIPS-BDRate without sacrificing more than 1 dB in PSNR.
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。