P-4DGS: Predictive 4D Gaussian Splatting with 90$\times$ Compression

• URL: http://arxiv.org/abs/2510.10030v1
• Date: Sat, 11 Oct 2025 05:19:41 GMT
• Title: P-4DGS: Predictive 4D Gaussian Splatting with 90$\times$ Compression
• Authors: Henan Wang, Hanxin Zhu, Xinliang Gong, Tianyu He, Xin Li, Zhibo Chen,
• Abstract summary: 3D Gaussian Splatting (3DGS) has garnered significant attention due to its superior scene representation fidelity and real-time rendering performance.<n>Despite achieving promising results, most existing algorithms overlook the substantial temporal and spatial redundancies inherent in dynamic scenes.<n>We propose P-4DGS, a novel dynamic 3DGS representation for compact 4D scene modeling.
• Score: 26.130131551764077
• License: http://creativecommons.org/publicdomain/zero/1.0/
• Abstract: 3D Gaussian Splatting (3DGS) has garnered significant attention due to its superior scene representation fidelity and real-time rendering performance, especially for dynamic 3D scene reconstruction (\textit{i.e.}, 4D reconstruction). However, despite achieving promising results, most existing algorithms overlook the substantial temporal and spatial redundancies inherent in dynamic scenes, leading to prohibitive memory consumption. To address this, we propose P-4DGS, a novel dynamic 3DGS representation for compact 4D scene modeling. Inspired by intra- and inter-frame prediction techniques commonly used in video compression, we first design a 3D anchor point-based spatial-temporal prediction module to fully exploit the spatial-temporal correlations across different 3D Gaussian primitives. Subsequently, we employ an adaptive quantization strategy combined with context-based entropy coding to further reduce the size of the 3D anchor points, thereby achieving enhanced compression efficiency. To evaluate the rate-distortion performance of our proposed P-4DGS in comparison with other dynamic 3DGS representations, we conduct extensive experiments on both synthetic and real-world datasets. Experimental results demonstrate that our approach achieves state-of-the-art reconstruction quality and the fastest rendering speed, with a remarkably low storage footprint (around \textbf{1MB} on average), achieving up to \textbf{40$\times$} and \textbf{90$\times$} compression on synthetic and real-world scenes, respectively.

Related papers

• EVolSplat4D: Efficient Volume-based Gaussian Splatting for 4D Urban Scene Synthesis [43.898895514609286]
  EvolSplat4D is a feed-forward framework that moves beyond existing per-pixel paradigms by unifying volume-based and pixel-based Gaussian prediction.<n>We show that EvolSplat4D reconstructs both static and dynamic environments with superior accuracy and consistency, outperforming both per-scene optimization and state-of-the-art feed-forward baselines.
  arXiv  Detail & Related papers  (2026-01-22T13:39:29Z)
• SUCCESS-GS: Survey of Compactness and Compression for Efficient Static and Dynamic Gaussian Splatting [12.927009543427259]
  3D Gaussian Splatting (3DGS) has emerged as a powerful explicit representation enabling real-time, high-fidelity 3D reconstruction and novel view synthesis.<n>However, its practical use is hindered by the massive memory and computational demands required to store and render millions of Gaussians.<n>This survey provides the first unified overview of efficient 3D and 4D Gaussian Splatting techniques.
  arXiv  Detail & Related papers  (2025-12-08T06:15:59Z)
• TED-4DGS: Temporally Activated and Embedding-based Deformation for 4DGS Compression [14.026420167067117]
  We present TED-4DGS, a temporally activated and embedding-based deformation scheme for rate-distortion-optimized 4DGS compression.<n>Our scheme achieves state-of-the-art rate-distortion performance on several real-world datasets.
  arXiv  Detail & Related papers  (2025-12-05T05:46:35Z)
• Diff4Splat: Controllable 4D Scene Generation with Latent Dynamic Reconstruction Models [79.06910348413861]
  We introduce Diff4Splat, a feed-forward method that synthesizes controllable and explicit 4D scenes from a single image.<n>Given a single input image, a camera trajectory, and an optional text prompt, Diff4Splat directly predicts a deformable 3D Gaussian field that encodes appearance, geometry, and motion.
  arXiv  Detail & Related papers  (2025-11-01T11:16:25Z)
• Speedy Deformable 3D Gaussian Splatting: Fast Rendering and Compression of Dynamic Scenes [57.69608119350651]
  Recent extensions of 3D Gaussian Splatting (3DGS) to dynamic scenes achieve high-quality novel view synthesis by using neural networks to predict the time-varying deformation of each Gaussian.<n>However, performing per-Gaussian neural inference at every frame poses a significant bottleneck, limiting rendering speed and increasing memory and compute requirements.<n>We present Speedy Deformable 3D Gaussian Splatting (SpeeDe3DGS), a general pipeline for accelerating the rendering speed of dynamic 3DGS and 4DGS representations by reducing neural inference through two complementary techniques.
  arXiv  Detail & Related papers  (2025-06-09T16:30:48Z)
• Disentangled 4D Gaussian Splatting: Towards Faster and More Efficient Dynamic Scene Rendering [12.27734287104036]
  Novel-entangleview synthesis (NVS) for dynamic scenes from 2D images presents significant challenges.<n>We introduce Disentangled 4D Gaussianting (Disentangled4DGS), a novel representation and rendering approach that disentangles temporal and spatial deformations.<n>Our approach achieves an unprecedented average rendering speed of 343 FPS at a resolution of $1352times1014$ on a 3090 GPU.
  arXiv  Detail & Related papers  (2025-03-28T05:46:02Z)
• 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)
• 4DGC: Rate-Aware 4D Gaussian Compression for Efficient Streamable Free-Viewpoint Video [56.04182926886754]
  3D Gaussian Splatting (3DGS) has substantial potential for enabling photorealistic Free-Viewpoint Video (FVV) experiences.<n>Existing methods typically handle dynamic 3DGS representation and compression separately, motion information and the rate-distortion trade-off during training.<n>We propose 4DGC, a rate-aware 4D Gaussian compression framework that significantly reduces storage size while maintaining superior RD performance for FVV.
  arXiv  Detail & Related papers  (2025-03-24T08:05:27Z)
• Light4GS: Lightweight Compact 4D Gaussian Splatting Generation via Context Model [21.375070073632944]
  3D view synthesisting (3DGS) has emerged as an efficient high-fidelity paradigm for novel and novel content.<n>To adapt 3DGS for dynamic content, deformable 3DGS incorporates temporally deformable primitives with learnable latent embeddings to capture complex motions.<n>Despite its impressive performance, the high-dimensional embeddings and vast number of primitives lead to substantial storage requirements.
  arXiv  Detail & Related papers  (2025-03-18T06:28:13Z)
• Locality-aware Gaussian Compression for Fast and High-quality Rendering [37.16956462469969]
  We present LocoGS, a locality-aware 3D Gaussian Splatting (3DGS) framework that exploits the spatial coherence of 3D Gaussians for compact modeling of scenes.<n>We first analyze the local coherence of 3D Gaussian attributes, and propose a novel locality-aware 3D Gaussian representation that effectively encodes locally-coherent Gaussian attributes.
  arXiv  Detail & Related papers  (2025-01-10T07:19:41Z)
• 4D Gaussian Splatting: Modeling Dynamic Scenes with Native 4D Primitives [115.67081491747943]
  Dynamic 3D scene representation and novel view synthesis are crucial for enabling AR/VR and metaverse applications.<n>We reformulate the reconstruction of a time-varying 3D scene as approximating its underlying 4D volume.<n>We derive several compact variants that effectively reduce the memory footprint to address its storage bottleneck.
  arXiv  Detail & Related papers  (2024-12-30T05:30:26Z)
• UrbanGS: Semantic-Guided Gaussian Splatting for Urban Scene Reconstruction [86.4386398262018]
  UrbanGS uses 2D semantic maps and an existing dynamic Gaussian approach to distinguish static objects from the scene.<n>For potentially dynamic objects, we aggregate temporal information using learnable time embeddings.<n>Our approach outperforms state-of-the-art methods in reconstruction quality and efficiency.
  arXiv  Detail & Related papers  (2024-12-04T16:59:49Z)
• 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)

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.