Frequency Disentangled Features in Neural Image Compression

• URL: http://arxiv.org/abs/2308.02620v1
• Date: Fri, 4 Aug 2023 14:55:44 GMT
• Title: Frequency Disentangled Features in Neural Image Compression
• Authors: Ali Zafari, Atefeh Khoshkhahtinat, Piyush Mehta, Mohammad Saeed Ebrahimi Saadabadi, Mohammad Akyash, Nasser M. Nasrabadi
• Abstract summary: A neural image compression network is governed by how well the entropy model matches the true distribution of the latent code. In this paper, we propose a feature-level frequency disentanglement to help the relaxed scalar quantization achieve lower bit rates. The proposed network not only outperforms hand-engineered codecs, but also neural network-based codecs built on-heavy spatially autoregressive entropy models.
• Score: 13.016298207860974
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: The design of a neural image compression network is governed by how well the entropy model matches the true distribution of the latent code. Apart from the model capacity, this ability is indirectly under the effect of how close the relaxed quantization is to the actual hard quantization. Optimizing the parameters of a rate-distortion variational autoencoder (R-D VAE) is ruled by this approximated quantization scheme. In this paper, we propose a feature-level frequency disentanglement to help the relaxed scalar quantization achieve lower bit rates by guiding the high entropy latent features to include most of the low-frequency texture of the image. In addition, to strengthen the de-correlating power of the transformer-based analysis/synthesis transform, an augmented self-attention score calculation based on the Hadamard product is utilized during both encoding and decoding. Channel-wise autoregressive entropy modeling takes advantage of the proposed frequency separation as it inherently directs high-informational low-frequency channels to the first chunks and conditions the future chunks on it. The proposed network not only outperforms hand-engineered codecs, but also neural network-based codecs built on computation-heavy spatially autoregressive entropy models.

Related papers

• Approximately Invertible Neural Network for Learned Image Compression [19.330720001489937]
  This paper proposes an Approximately Invertible Neural Network (A-INN) framework for learned image compression. It formulates the rate-distortion optimization in lossy image compression when using INN with quantization. Extensive experiments demonstrate that the proposed A-INN outperforms the existing learned image compression methods.
  arXiv  Detail & Related papers  (2024-08-30T07:57:47Z)
• Laplacian-guided Entropy Model in Neural Codec with Blur-dissipated Synthesis [10.428185253933004]
  We replace Gaussian decoders with a non-isotropic diffusion model at the decoder side. Our framework is equipped with a novel entropy model that accurately models probability distribution latent representation. Our experiments demonstrate that our framework yields better perceptual quality compared to cutting-edge generative entropy-based codecs.
  arXiv  Detail & Related papers  (2024-03-24T18:33:16Z)
• Joint Hierarchical Priors and Adaptive Spatial Resolution for Efficient Neural Image Compression [11.25130799452367]
  We propose an absolute image compression transformer (ICT) for neural image compression (NIC) ICT captures both global and local contexts from the latent representations and better parameterize the distribution of the quantized latents. Our framework significantly improves the trade-off between coding efficiency and decoder complexity over the versatile video coding (VVC) reference encoder (VTM-18.0) and the neural SwinT-ChARM.
  arXiv  Detail & Related papers  (2023-07-05T13:17:14Z)
• Compression with Bayesian Implicit Neural Representations [16.593537431810237]
  We propose overfitting variational neural networks to the data and compressing an approximate posterior weight sample using relative entropy coding instead of quantizing and entropy coding it. Experiments show that our method achieves strong performance on image and audio compression while retaining simplicity.
  arXiv  Detail & Related papers  (2023-05-30T16:29:52Z)
• The END: An Equivariant Neural Decoder for Quantum Error Correction [73.4384623973809]
  We introduce a data efficient neural decoder that exploits the symmetries of the problem. We propose a novel equivariant architecture that achieves state of the art accuracy compared to previous neural decoders.
  arXiv  Detail & Related papers  (2023-04-14T19:46:39Z)
• Q-Diffusion: Quantizing Diffusion Models [52.978047249670276]
  Post-training quantization (PTQ) is considered a go-to compression method for other tasks. We propose a novel PTQ method specifically tailored towards the unique multi-timestep pipeline and model architecture. We show that our proposed method is able to quantize full-precision unconditional diffusion models into 4-bit while maintaining comparable performance.
  arXiv  Detail & Related papers  (2023-02-08T19:38:59Z)
• NAF: Neural Attenuation Fields for Sparse-View CBCT Reconstruction [79.13750275141139]
  This paper proposes a novel and fast self-supervised solution for sparse-view CBCT reconstruction. The desired attenuation coefficients are represented as a continuous function of 3D spatial coordinates, parameterized by a fully-connected deep neural network. A learning-based encoder entailing hash coding is adopted to help the network capture high-frequency details.
  arXiv  Detail & Related papers  (2022-09-29T04:06:00Z)
• Hybrid Spatial-Temporal Entropy Modelling for Neural Video Compression [25.96187914295921]
  This paper proposes a powerful entropy model which efficiently captures both spatial and temporal dependencies. Our entropy model can achieve 18.2% saving on UVG dataset when compared with H266 (VTM) using the highest compression ratio.
  arXiv  Detail & Related papers  (2022-07-13T00:03:54Z)
• Neural Data-Dependent Transform for Learned Image Compression [72.86505042102155]
  We build a neural data-dependent transform and introduce a continuous online mode decision mechanism to jointly optimize the coding efficiency for each individual image. The experimental results show the effectiveness of the proposed neural-syntax design and the continuous online mode decision mechanism.
  arXiv  Detail & Related papers  (2022-03-09T14:56:48Z)
• Rate Distortion Characteristic Modeling for Neural Image Compression [59.25700168404325]
  End-to-end optimization capability offers neural image compression (NIC) superior lossy compression performance. distinct models are required to be trained to reach different points in the rate-distortion (R-D) space. We make efforts to formulate the essential mathematical functions to describe the R-D behavior of NIC using deep network and statistical modeling.
  arXiv  Detail & Related papers  (2021-06-24T12:23:05Z)
• Learning Context-Based Non-local Entropy Modeling for Image Compression [140.64888994506313]
  In this paper, we propose a non-local operation for context modeling by employing the global similarity within the context. The entropy model is further adopted as the rate loss in a joint rate-distortion optimization. Considering that the width of the transforms is essential in training low distortion models, we finally produce a U-Net block in the transforms to increase the width with manageable memory consumption and time complexity.
  arXiv  Detail & Related papers  (2020-05-10T13:28:18Z)

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.