Clustered Codebook Quantization for 2D Gaussian-based Image Compression

• URL: http://arxiv.org/abs/2607.05667v1
• Date: Mon, 06 Jul 2026 22:16:37 GMT
• Title: Clustered Codebook Quantization for 2D Gaussian-based Image Compression
• Abstract summary: Cluster-Guided Vector Quantization (CGVQ) is a primitive based image compression method.<n>We show that CGVQ decreases the bpp by 20% with respect to our baseline, while maintaining on-par visual quality.
• Score: 0.09332987715848712
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Gaussian-based image representations effectively model image content using compact parametric primitives while preserving high visual fidelity, yet storing a large number of floating-point parameters per primitive degrades rate-distortion efficiency at higher fidelity targets. To improve the rate-distortion performance in Gaussian representation, we present our Cluster-Guided Vector Quantization (CGVQ), a Gaussian primitive based image compression method. Our key idea is to partition Gaussian parameters further into homogeneous groups prior to quantization, enabling higher compression efficiency and accurate parameter reconstruction. In practice, our extensive experiments show that CGVQ decreases the bpp by 20% with respect to our baseline, while maintaining on-par visual quality

Related papers

• GS^2: Graph-based Spatial Distribution Optimization for Compact 3D Gaussian Splatting [50.2045409672451]
  3D Gaussian Splatting (3DGS) has demonstrated breakthrough performance in novel view synthesis and real-time rendering.<n>It is constrained by the high memory cost due to a huge number of Gaussian points.<n>We propose graph-based spatial distribution optimization for compact 3DGS.
  arXiv  Detail & Related papers  (2026-04-02T10:41:51Z)
• SGI: Structured 2D Gaussians for Efficient and Compact Large Image Representation [15.343904266924445]
  2D Gaussian Splatting has emerged as a novel image representation technique that can support efficient rendering on low-end devices.<n>We propose Structured Gaussian Image (SGI), a compact and efficient framework for representing high-resolution images.<n>SGI decomposes a complex image into multi-scale local spaces defined by a set of seeds.
  arXiv  Detail & Related papers  (2026-03-08T20:14:19Z)
• GaussianImage++: Boosted Image Representation and Compression with 2D Gaussian Splatting [29.353296699942117]
  Implicit neural representations (INRs) have achieved remarkable success in image representation and compression.<n>Recent 2D Gaussian Splatting (GS) methods offer promising alternatives through efficient primitive-based rendering.<n>We present GaussianImage++, which utilizes limited Gaussian primitives to achieve impressive representation and compression performance.
  arXiv  Detail & Related papers  (2025-12-22T07:22:39Z)
• ProtoGS: Efficient and High-Quality Rendering with 3D Gaussian Prototypes [81.48624894781257]
  3D Gaussian Splatting (3DGS) has made significant strides in novel view synthesis but is limited by the substantial number of Gaussian primitives required.<n>Recent methods address this issue by compressing the storage size of densified Gaussians, yet fail to preserve rendering quality and efficiency.<n>We propose ProtoGS to learn Gaussian prototypes to represent Gaussian primitives, significantly reducing the total Gaussian amount without sacrificing visual quality.
  arXiv  Detail & Related papers  (2025-03-21T18:55:14Z)
• EigenGS Representation: From Eigenspace to Gaussian Image Space [20.454762899389358]
  EigenGS is an efficient transformation pipeline connecting eigenspace and image-space Gaussian representations.<n>We show that EigenGS achieves superior reconstruction quality compared to direct 2D Gaussian fitting.<n>The results highlight EigenGS's effectiveness and generalization ability across images with varying resolutions and diverse categories.
  arXiv  Detail & Related papers  (2025-03-10T15:27:03Z)
• GaussianToken: An Effective Image Tokenizer with 2D Gaussian Splatting [64.84383010238908]
  We propose an effective image tokenizer with 2D Gaussian Splatting as a solution.<n>In general, our framework integrates the local influence of 2D Gaussian distribution into the discrete space.<n> Competitive reconstruction performances on CIFAR, Mini-Net, and ImageNet-1K demonstrate the effectiveness of our framework.
  arXiv  Detail & Related papers  (2025-01-26T17:56:11Z)
• CompGS: Efficient 3D Scene Representation via Compressed Gaussian Splatting [68.94594215660473]
  We propose an efficient 3D scene representation, named Compressed Gaussian Splatting (CompGS) We exploit a small set of anchor primitives for prediction, allowing the majority of primitives to be encapsulated into highly compact residual forms. Experimental results show that the proposed CompGS significantly outperforms existing methods, achieving superior compactness in 3D scene representation without compromising model accuracy and rendering quality.
  arXiv  Detail & Related papers  (2024-04-15T04:50:39Z)
• HiFi4G: High-Fidelity Human Performance Rendering via Compact Gaussian Splatting [48.59338619051709]
  HiFi4G is an explicit and compact Gaussian-based approach for high-fidelity human performance rendering from dense footage. It achieves a substantial compression rate of approximately 25 times, with less than 2MB of storage per frame.
  arXiv  Detail & Related papers  (2023-12-06T12:36:53Z)
• High-Perceptual Quality JPEG Decoding via Posterior Sampling [13.238373528922194]
  We propose a different paradigm for JPEG artifact correction. We aim to obtain sharp, detailed and visually reconstructed images, while being consistent with the compressed input. Our solution offers a diverse set of plausible and fast reconstructions for a given input with perfect consistency.
  arXiv  Detail & Related papers  (2022-11-21T19:47:59Z)
• Unified Multivariate Gaussian Mixture for Efficient Neural Image Compression [151.3826781154146]
  latent variables with priors and hyperpriors is an essential problem in variational image compression. We find inter-correlations and intra-correlations exist when observing latent variables in a vectorized perspective. Our model has better rate-distortion performance and an impressive $3.18times$ compression speed up.
  arXiv  Detail & Related papers  (2022-03-21T11:44:17Z)
• Asymmetric Gained Deep Image Compression With Continuous Rate Adaptation [12.009880944927069]
  We propose a continuously rate adjustable learned image compression framework, Asymmetric Gained Variational Autoencoder (AG-VAE) AG-VAE utilizes a pair of gain units to achieve discrete rate adaptation in one single model with a negligible additional computation. Our method achieves comparable quantitative performance with SOTA learned image compression methods and better qualitative performance than classical image codecs.
  arXiv  Detail & Related papers  (2020-03-04T11:42:05Z)

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.