Research
Multiple Scale Latents for Learned Image Compression
arXiv:2608.10952v1 Announce Type: new Abstract: Most learned image compression systems rely on a single latent representation combined with a hyperprior, which limits their ability to efficiently capt
arXiv:2608.10952v1 Announce Type: new Abstract: Most learned image compression systems rely on a single latent representation combined with a hyperprior, which limits their ability to efficiently capture image structure across spatial scales. In this work, we propose a hierarchical latent representation to improve the efficiency of the entropy model. By using multiple latents at different scales, each with its own entropy model, we better capture the spatial structure of the latent representation. Our experiments show that this approach achieves a 17.9% BD-rate reduction over VVC on Kodak, demonstrating the effectiveness of multi-scale latent representations. Furthermore, the approach is orthogonal to other advances in learned image compression, making it a versatile addition to existing methods.
Related
- Efficient Learned Image Compression without Entropy Coding
- Dual-Latent Collaborative Decoding for Fidelity-Perception Balanced Image Compression
- ProGIC: Progressive and Lightweight Generative Image Compression with Residual Vector Quantization
Source: arXiv cs.CV | 2026-08-12