基于浅层编码器的超低码率感知图像压缩
Ultra-Low Bitrate Perceptual Image Compression with Shallow Encoder
用浅层编码器加单步扩散解码器做非对称极低码率压缩，为边缘设备上的图像传输提供了可复用的「轻编码、重解码」范式，其中双侧特征蒸馏可迁移到其他编码器轻量化场景。
原文依据 AEIC employs moderate or even shallow encoder networks, while leveraging an one-step diffusion decoder
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论超低码率图像压缩（低于每像素 0.05 比特）对于带宽受限、计算受限的编码场景（如边缘设备）日益关键。现有框架通常依赖大型预训练编码器（如 VAE 或基于 tokenizer 的模型），并在其生成潜变量空间中执行变换编码。尽管这些方法取得了令人印象深刻的感知保真度，但其对重型编码器网络的依赖使其不适合部署在算力较弱的发送端设备上。本文探索了将浅层编码器用于超低码率压缩的可行性，并提出了一种新颖的非对称极端图像压缩（AEIC）框架，同时追求编码的简洁性与解码的质量。具体而言，AEIC 采用中等甚至浅层的编码器网络，同时利用单步扩散解码器在极端码率下保持高保真与高真实感的重建。为进一步提升浅层编码器的效率，我们设计了一种双侧特征蒸馏方案，将带有中等编码器的 AEIC 的知识迁移到其浅层编码器变体。实验表明，AEIC 不仅在超低码率下的率-失真-感知性能上优于现有方法，而且在 1080P 图像上以 35.8 FPS 实现了出色的编码效率，同时与现有方法相比保持了有竞争力的解码速度。代码见 https://github.com/LuizScarlet/AEIC。
英文原文摘要 1501 字符
Ultra-low bitrate image compression (below 0.05 bits per pixel) is increasingly critical for bandwidth-constrained and computation-limited encoding scenarios such as edge devices. Existing frameworks typically rely on large pretrained encoders (e.g., VAEs or tokenizer-based models) and perform transform coding within their generative latent space. While these approaches achieve impressive perceptual fidelity, their reliance on heavy encoder networks makes them unsuitable for deployment on weak sender devices. In this work, we explore the feasibility of applying shallow encoders for ultra-low bitrate compression and propose a novel Asymmetric Extreme Image Compression (AEIC) framework that pursues simultaneously encoding simplicity and decoding quality. Specifically, AEIC employs moderate or even shallow encoder networks, while leveraging an one-step diffusion decoder to maintain high-fidelity and high-realism reconstructions under extreme bitrates. To further enhance the efficiency of shallow encoders, we design a dual-side feature distillation scheme that transfers knowledge from AEIC with moderate encoders to its shallow encoder variants. Experiments show that AEIC not only outperforms existing methods on rate-distortion-perception performance at ultra-low bitrates, but also delivers exceptional encoding efficiency for 35.8 FPS on 1080P images, while maintaining competitive decoding speed compared to existing methods. Code is available at https://github.com/LuizScarlet/AEIC.