TreeNet用树状结构实现低比特率图像压缩，效率远超现有方案。
TreeNet: A Light Weight Model for Low Bitrate Image Compression
- 采用二叉树架构的编码解码器，减少计算复杂度。
- 低比特率下比JPEG AI平均提升4.83%的压缩性能。
- 适合资源受限设备部署，对模型轻量化有参考价值。
降低计算复杂度仍是学习型图像压缩技术广泛应用的关键挑战。本文提出TreeNet，一种新颖的低复杂度图像压缩模型，利用二叉树结构的编码解码器实现高效表征与重建。通过注意力特征融合机制，有效整合多分支特征。我们在三个常用基准数据集上评估TreeNet，与包括JPEG AI在内的竞争方法对比。在低比特率下，TreeNet相比JPEG AI平均提升4.83%的BD-rate，同时模型复杂度降低87.82%。此外，我们进行了广泛的消融实验，探究了树状结构中不同潜在表示的影响，深化了对重建质量贡献因素的理解。
原文摘要 · Abstract (English)
Reducing computational complexity remains a critical challenge for the widespread adoption of learning-based image compression techniques. In this work, we propose TreeNet, a novel low-complexity image compression model that leverages a binary tree-structured encoder-decoder architecture to achieve efficient representation and reconstruction. We employ attentional feature fusion mechanism to effectively integrate features from multiple branches. We evaluate TreeNet on three widely used benchmark datasets and compare its performance against competing methods including JPEG AI, a recent standard in learning-based image compression. At low bitrates, TreeNet achieves an average improvement of 4.83% in BD-rate over JPEG AI, while reducing model complexity by 87.82%. Furthermore, we conduct extensive ablation studies to investigate the influence of various latent representations within TreeNet, offering deeper insights into the factors contributing to reconstruction.
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。