用扩散模型去噪提升图像压缩质量，尤其擅长恢复破损或带噪图片
Edge-based Denoising Image Compression
- 在潜空间中利用边缘等关键信息进行去噪重建
- 在部分数据丢失或噪声严重时仍保持高质量还原
- 适合对压缩后图像保真度要求高的场景
近年来，基于深度学习的图像压缩，尤其是生成模型，已成为研究热点。尽管取得了显著进展，但重构图像清晰度下降、学习效率低（如模式崩溃）以及传输过程中的数据丢失等问题依然存在。为此，我们提出一种新型压缩模型，引入基于扩散模型的去噪步骤，通过利用潜空间中的子信息（如边缘和深度）显著提升图像重建的保真度。实验证明，该模型在图像质量和压缩效率上均达到或优于现有方法。尤其在部分图像丢失或噪声过大的情况下，通过引入边缘估计网络，有效保持了重构图像的完整性，为当前图像压缩的局限性提供了一种稳健解决方案。
原文摘要 · Abstract (English)
In recent years, deep learning-based image compression, particularly through generative models, has emerged as a pivotal area of research. Despite significant advancements, challenges such as diminished sharpness and quality in reconstructed images, learning inefficiencies due to mode collapse, and data loss during transmission persist. To address these issues, we propose a novel compression model that incorporates a denoising step with diffusion models, significantly enhancing image reconstruction fidelity by sub-information(e.g., edge and depth) from leveraging latent space. Empirical experiments demonstrate that our model achieves superior or comparable results in terms of image quality and compression efficiency when measured against the existing models. Notably, our model excels in scenarios of partial image loss or excessive noise by introducing an edge estimation network to preserve the integrity of reconstructed images, offering a robust solution to the current limitations of image 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。