Compression of 3D Gaussian Splatting Data Using GPU-friendly Graphics Texture Coding

• URL: http://arxiv.org/abs/2607.14513v1
• Date: Thu, 16 Jul 2026 03:10:27 GMT
• Title: Compression of 3D Gaussian Splatting Data Using GPU-friendly Graphics Texture Coding
• Abstract summary: In 3DGS, spherical harmonic (SH) are employed to model view-dependent color, resulting in a large number of SH coefficients per primitive and large memory requirements.<n>We propose a method for compressing SH color coefficients using texture compression schemes specifically designed for efficient parallel GPU decoding.
• Score: 2.740558005015499
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Techniques for modeling 3D scenes from image collections, such as 3D Gaussian Splatting (3DGS), are capable of generating high-quality novel views by leveraging graphics primitives with view-dependent appearance. In 3DGS, spherical harmonic (SH) are employed to model view-dependent color, resulting in a large number of SH coefficients per primitive and large memory requirements. While compression approaches have been proposed to mitigate this problem, they do not exploit the capabilities of modern Graphics Processing Units (GPUs) for parallel decoding and rendering. In this paper, we propose a method for compressing SH color coefficients using texture compression schemes specifically designed for efficient parallel GPU decoding and supported by dedicated hardware acceleration. It is shown that those methods can compress color coefficients more effectively than 2D textures by exploiting the fact that primitives can be locally grouped and reordered according to color. Furthermore, we introduce a bit-rate control strategy that preserves random access, enabling large-scale parallelization without compromising rendering performance. Experimental results using BC1 and BC7 texture compression formats show that GPU-based decompression can be achieved with negligible or imperceptible degradation in the visual quality of rendered 3DGS scenes.

Related papers

• GS-NFS: Bandwidth-adaptive Streaming of Dynamic Gaussian Splats and Point Clouds [27.401745355020086]
  GS-NFS accelerates dynamic 3DGS compression and decompression on a GPU.<n>It is 1-2 orders of magnitude faster than the state-of-the-art in encoding and decoding a frame.
  arXiv  Detail & Related papers  (2026-06-04T03:27:56Z)
• IBGS: Image-Based Gaussian Splatting [17.07390802338029]
  3D Gaussian Splatting (3DGS) has recently emerged as a fast, high-quality method for novel view synthesis (NVS)<n>We propose Image-Based Gaussian Splatting, an efficient alternative that leverages high-resolution source images for fine details and view-specific color modeling.<n> Experiments on standard NVS benchmarks show that our method significantly outperforms prior Gaussian Splatting approaches in rendering quality, without increasing the storage footprint.
  arXiv  Detail & Related papers  (2025-11-18T11:03:27Z)
• EVolSplat: Efficient Volume-based Gaussian Splatting for Urban View Synthesis [61.1662426227688]
  Existing NeRF and 3DGS-based methods show promising results in achieving photorealistic renderings but require slow, per-scene optimization.<n>We introduce EVolSplat, an efficient 3D Gaussian Splatting model for urban scenes that works in a feed-forward manner.
  arXiv  Detail & Related papers  (2025-03-26T02:47:27Z)
• Temporally Compressed 3D Gaussian Splatting for Dynamic Scenes [46.64784407920817]
  Temporally Compressed 3D Gaussian Splatting (TC3DGS) is a novel technique designed specifically to compress dynamic 3D Gaussian representations.<n>Our experiments across multiple datasets demonstrate that TC3DGS achieves up to 67$times$ compression with minimal or no degradation in visual quality.
  arXiv  Detail & Related papers  (2024-12-07T17:03:09Z)
• EVER: Exact Volumetric Ellipsoid Rendering for Real-time View Synthesis [72.53316783628803]
  We present Exact Volumetric Ellipsoid Rendering (EVER), a method for real-time differentiable emission-only volume rendering.<n>Unlike recentization based approach by 3D Gaussian Splatting (3DGS), our primitive based representation allows for exact volume rendering.<n>We show that our method is more accurate with blending issues than 3DGS and follow-up work on view rendering.
  arXiv  Detail & Related papers  (2024-10-02T17:59:09Z)
• Plenoptic PNG: Real-Time Neural Radiance Fields in 150 KB [29.267039546199094]
  This paper aims to encode a 3D scene into an extremely compact representation from 2D images. It enables its transmittance, decoding and rendering in real-time across various platforms.
  arXiv  Detail & Related papers  (2024-09-24T03:06:22Z)
• Image-GS: Content-Adaptive Image Representation via 2D Gaussians [52.598772767324036]
  We introduce Image-GS, a content-adaptive image representation based on 2D Gaussians radiance.<n>It supports hardware-friendly rapid access for real-time usage, requiring only 0.3K MACs to decode a pixel.<n>We demonstrate its versatility with several applications, including texture compression, semantics-aware compression, and joint image compression and restoration.
  arXiv  Detail & Related papers  (2024-07-02T00:45:21Z)
• SAGS: Structure-Aware 3D Gaussian Splatting [53.6730827668389]
  We propose a structure-aware Gaussian Splatting method (SAGS) that implicitly encodes the geometry of the scene. SAGS reflects to state-of-the-art rendering performance and reduced storage requirements on benchmark novel-view synthesis datasets.
  arXiv  Detail & Related papers  (2024-04-29T23:26:30Z)
• 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)
• Sketch3D: Style-Consistent Guidance for Sketch-to-3D Generation [55.73399465968594]
  This paper proposes a novel generation paradigm Sketch3D to generate realistic 3D assets with shape aligned with the input sketch and color matching the textual description. Three strategies are designed to optimize 3D Gaussians, i.e., structural optimization via a distribution transfer mechanism, color optimization with a straightforward MSE loss and sketch similarity optimization with a CLIP-based geometric similarity loss.
  arXiv  Detail & Related papers  (2024-04-02T11:03:24Z)
• Compressed 3D Gaussian Splatting for Accelerated Novel View Synthesis [0.552480439325792]
  High-fidelity scene reconstruction with an optimized 3D Gaussian splat representation has been introduced for novel view synthesis from sparse image sets. We propose a compressed 3D Gaussian splat representation that utilizes sensitivity-aware vector clustering with quantization-aware training to compress directional colors and Gaussian parameters.
  arXiv  Detail & Related papers  (2023-11-17T14:40:43Z)

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.