From Noise to Latent: Generating Gaussian Latents for INR-Based Image Compression

• URL: http://arxiv.org/abs/2511.08009v1
• Date: Wed, 12 Nov 2025 01:33:45 GMT
• Title: From Noise to Latent: Generating Gaussian Latents for INR-Based Image Compression
• Authors: Chaoyi Lin, Yaojun Wu, Yue Li, Junru Li, Kai Zhang, Li Zhang,
• Abstract summary: Recent implicit neural representation (INR)-based image compression methods have shown competitive performance by overfitting image-specific latent codes.<n>We propose a novel image compression paradigm that reconstructs image-specific latents from a multi-scale Gaussian noise, deterministically generated using a shared random seed.<n>Our method eliminates the need to transmit latent codes while preserving latent-based benefits, achieving competitive rate-distortion performance on Kodak and CLIC dataset.
• Score: 15.519085773825656
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Recent implicit neural representation (INR)-based image compression methods have shown competitive performance by overfitting image-specific latent codes. However, they remain inferior to end-to-end (E2E) compression approaches due to the absence of expressive latent representations. On the other hand, E2E methods rely on transmitting latent codes and requiring complex entropy models, leading to increased decoding complexity. Inspired by the normalization strategy in E2E codecs where latents are transformed into Gaussian noise to demonstrate the removal of spatial redundancy, we explore the inverse direction: generating latents directly from Gaussian noise. In this paper, we propose a novel image compression paradigm that reconstructs image-specific latents from a multi-scale Gaussian noise tensor, deterministically generated using a shared random seed. A Gaussian Parameter Prediction (GPP) module estimates the distribution parameters, enabling one-shot latent generation via reparameterization trick. The predicted latent is then passed through a synthesis network to reconstruct the image. Our method eliminates the need to transmit latent codes while preserving latent-based benefits, achieving competitive rate-distortion performance on Kodak and CLIC dataset. To the best of our knowledge, this is the first work to explore Gaussian latent generation for learned image compression.

Related papers

• Perception-based Image Denoising via Generative Compression [5.85669274676101]
  Image denoising aims to remove noise while preserving structural details and perceptual realism.<n> distortion-driven methods often produce over-smoothed reconstructions, especially under strong noise and distribution shift.<n>This paper proposes a generative compression framework for perception-based denoising.
  arXiv  Detail & Related papers  (2026-02-12T04:21:26Z)
• Generative Image Compression by Estimating Gradients of the Rate-variable Feature Distribution [37.60572296105984]
  We propose a novel diffusion-based generative modeling framework tailored for generative image compression.<n>A reverse neural network is trained to reconstruct images by reversing the compression process directly.<n>This approach achieves smooth rate adjustment and photo-realistic reconstructions with only a minimal number of sampling steps.
  arXiv  Detail & Related papers  (2025-05-27T10:18:24Z)
• OSCAR: One-Step Diffusion Codec Across Multiple Bit-rates [39.746866725267516]
  Pretrained latent diffusion models have shown strong potential for lossy image compression.<n>We propose a one-step diffusion across multiple bit-rates termed OSCAR.<n>Experiments demonstrate that OSCAR achieves superior performance in both quantitative and visual quality metrics.
  arXiv  Detail & Related papers  (2025-05-22T00:14:12Z)
• Higher fidelity perceptual image and video compression with a latent conditioned residual denoising diffusion model [55.2480439325792]
  We propose a hybrid compression scheme optimized for perceptual quality, extending the approach of the CDC model with a decoder network.<n>We achieve up to +2dB PSNR fidelity improvements while maintaining comparable LPIPS and FID perceptual scores when compared with CDC.
  arXiv  Detail & Related papers  (2025-05-19T14:13:14Z)
• 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)
• Compressed Image Generation with Denoising Diffusion Codebook Models [31.58365182858562]
  We present a novel generative approach that produces high-quality image samples along with their losslessly compressed bit-stream representations.<n>This is obtained by replacing the standard Gaussian noise sampling in the reverse diffusion with a selection of noise samples from pre-defined codebooks of fixed iid Gaussian vectors.<n>We leverage DDCM and pick the noises from the codebooks that best match a given image, converting our generative model into a highly effective lossy image.
  arXiv  Detail & Related papers  (2025-02-03T09:25:57Z)
• 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)
• Semantic Ensemble Loss and Latent Refinement for High-Fidelity Neural Image Compression [58.618625678054826]
  This study presents an enhanced neural compression method designed for optimal visual fidelity. We have trained our model with a sophisticated semantic ensemble loss, integrating Charbonnier loss, perceptual loss, style loss, and a non-binary adversarial loss. Our empirical findings demonstrate that this approach significantly improves the statistical fidelity of neural image compression.
  arXiv  Detail & Related papers  (2024-01-25T08:11:27Z)
• Modality-Agnostic Variational Compression of Implicit Neural Representations [96.35492043867104]
  We introduce a modality-agnostic neural compression algorithm based on a functional view of data and parameterised as an Implicit Neural Representation (INR) Bridging the gap between latent coding and sparsity, we obtain compact latent representations non-linearly mapped to a soft gating mechanism. After obtaining a dataset of such latent representations, we directly optimise the rate/distortion trade-off in a modality-agnostic space using neural compression.
  arXiv  Detail & Related papers  (2023-01-23T15:22:42Z)
• Implicit Neural Representations for Image Compression [103.78615661013623]
  Implicit Neural Representations (INRs) have gained attention as a novel and effective representation for various data types. We propose the first comprehensive compression pipeline based on INRs including quantization, quantization-aware retraining and entropy coding. We find that our approach to source compression with INRs vastly outperforms similar prior work.
  arXiv  Detail & Related papers  (2021-12-08T13:02:53Z)
• Causal Contextual Prediction for Learned Image Compression [36.08393281509613]
  We propose the concept of separate entropy coding to leverage a serial decoding process for causal contextual entropy prediction in the latent space. A causal context model is proposed that separates the latents across channels and makes use of cross-channel relationships to generate highly informative contexts. We also propose a causal global prediction model, which is able to find global reference points for accurate predictions of unknown points.
  arXiv  Detail & Related papers  (2020-11-19T08:15:10Z)
• Modeling Lost Information in Lossy Image Compression [72.69327382643549]
  Lossy image compression is one of the most commonly used operators for digital images. We propose a novel invertible framework called Invertible Lossy Compression (ILC) to largely mitigate the information loss problem.
  arXiv  Detail & Related papers  (2020-06-22T04:04:56Z)

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.