Multiple Scale Latents for Learned Image Compression

• URL: http://arxiv.org/abs/2608.10952v1
• Date: Tue, 11 Aug 2026 14:22:20 GMT
• Title: Multiple Scale Latents for Learned Image Compression
• Abstract summary: We propose a hierarchical latent representation to improve the efficiency of the entropy model.<n>By using multiple latents at different scales, each with its own entropy model, we better capture the spatial structure of the latent representation.<n>Our experiments show that this approach achieves a 17.9% BD-rate reduction over VVC on Kodak.
• Score: 53.71337604556311
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• 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 papers

• Mixture-of-Experts-based Entropy Model for Learned Image Compression [53.71337604556311]
  We propose a MoE-based Entropy model (MoEE) for learned image compression.<n>Our model achieves a BD-Rate improvement over VVC of -16.85% on the Kodak dataset.
  arXiv  Detail & Related papers  (2026-08-11T14:17:39Z)
• SFTok: Bridging the Performance Gap in Discrete Tokenizers [72.9996757048065]
  We propose textbfSFTok, a discrete tokenizer that incorporates a multi-step iterative mechanism for precise reconstruction.<n>At a high compression rate of only 64 tokens per image, SFTok achieves state-of-the-art reconstruction quality on ImageNet.
  arXiv  Detail & Related papers  (2025-12-18T18:59:04Z)
• Multi-Scale Invertible Neural Network for Wide-Range Variable-Rate Learned Image Compression [90.59962443790593]
  In this paper, we present a variable-rate image compression model based on invertible transform to overcome limitations.<n> Specifically, we design a lightweight multi-scale invertible neural network, which maps the input image into multi-scale latent representations.<n> Experimental results demonstrate that the proposed method achieves state-of-the-art performance compared to existing variable-rate methods.
  arXiv  Detail & Related papers  (2025-03-27T09:08:39Z)
• MambaIC: State Space Models for High-Performance Learned Image Compression [40.155314987485376]
  A high-performance image compression algorithm is crucial for real-time information transmission across numerous fields.<n>Inspired by the effectiveness of state space models (SSMs) in capturing long-range dependencies, we leverage SSMs to address computational inefficiency in existing methods.<n>We propose an enhanced image compression approach through refined context modeling, which we term MambaIC.
  arXiv  Detail & Related papers  (2025-03-16T11:32:34Z)
• Diffusion-Based Hierarchical Image Steganography [60.69791384893602]
  Hierarchical Image Steganography is a novel method that enhances the security and capacity of embedding multiple images into a single container. It exploits the robustness of the Diffusion Model alongside the reversibility of the Flow Model. The innovative structure can autonomously generate a container image, thereby securely and efficiently concealing multiple images and text.
  arXiv  Detail & Related papers  (2024-05-19T11:29:52Z)
• Robustly overfitting latents for flexible neural image compression [1.7041035606170198]
  State-of-the-art neural image compression models learn to encode an image into a quantized latent representation that can be efficiently sent to the decoder. These models have proven successful in practice, but they lead to sub-optimal results due to imperfect optimization and limitations in the encoder and decoder capacity. Recent work shows how to use Gumbel annealing (SGA) to refine the latents of pre-trained neural image compression models. We show how our method improves the overall compression performance in terms of the R-D trade-off, compared to its predecessors.
  arXiv  Detail & Related papers  (2024-01-31T12:32:17Z)
• COMPASS: High-Efficiency Deep Image Compression with Arbitrary-scale Spatial Scalability [28.270200666064163]
  We propose a novel NN-based spatially scalable image compression method, called Compass, which supports arbitrary-scale spatial scalability. Our proposed Compass has a very flexible structure where the number of layers and their respective scale factors can be arbitrarily determined during inference. Experimental results show that our Compass achieves BD-rate gain of -58.33% and -47.17% at maximum compared to SHVC and the state-of-the-art NN-based spatially scalable image compression method, respectively.
  arXiv  Detail & Related papers  (2023-09-11T14:05:18Z)
• Optimizing Hierarchical Image VAEs for Sample Quality [0.0]
  hierarchical variational autoencoders (VAEs) have achieved great density estimation on image modeling tasks. We attribute this to learned representations that over-emphasize compressing imperceptible details of the image. We introduce a KL-reweighting strategy to control the amount of infor mation in each latent group, and employ a Gaussian output layer to reduce sharpness in the learning objective.
  arXiv  Detail & Related papers  (2022-10-18T23:10:58Z)
• DWDN: Deep Wiener Deconvolution Network for Non-Blind Image Deblurring [66.91879314310842]
  We propose an explicit deconvolution process in a feature space by integrating a classical Wiener deconvolution framework with learned deep features. A multi-scale cascaded feature refinement module then predicts the deblurred image from the deconvolved deep features. We show that the proposed deep Wiener deconvolution network facilitates deblurred results with visibly fewer artifacts and quantitatively outperforms state-of-the-art non-blind image deblurring methods by a wide margin.
  arXiv  Detail & Related papers  (2021-03-18T00:38:11Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.