Sketch&Patch++: Efficient Structure-Aware 3D Gaussian Representation

• URL: http://arxiv.org/abs/2601.05394v2
• Date: Mon, 12 Jan 2026 15:16:39 GMT
• Title: Sketch&Patch++: Efficient Structure-Aware 3D Gaussian Representation
• Authors: Yuang Shi, Géraldine Morin, Simone Gasparini, Wei Tsang Ooi,
• Abstract summary: We propose a hybrid representation that categorizes Gaussians into (i) Sketch Gaussians, which represent high-frequency, boundary-defining features, and (ii) Patch Gaussians, which cover low-frequency, smooth regions.<n>Our approach employs multi-criteria density-based clustering, combined with adaptive quality-driven refinement.<n>This structure-aware representation enables efficient storage, adaptive streaming, and rendering of high-fidelity 3D content across bandwidth-constrained networks and resource-limited devices.
• Score: 5.17519482656693
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: We observe that Gaussians exhibit distinct roles and characteristics analogous to traditional artistic techniques -- like how artists first sketch outlines before filling in broader areas with color, some Gaussians capture high-frequency features such as edges and contours, while others represent broader, smoother regions analogous to brush strokes that add volume and depth. Based on this observation, we propose a hybrid representation that categorizes Gaussians into (i) Sketch Gaussians, which represent high-frequency, boundary-defining features, and (ii) Patch Gaussians, which cover low-frequency, smooth regions. This semantic separation naturally enables layered progressive streaming, where the compact Sketch Gaussians establish the structural skeleton before Patch Gaussians incrementally refine volumetric detail. In this work, we extend our previous method to arbitrary 3D scenes by proposing a novel hierarchical adaptive categorization framework that operates directly on the 3DGS representation. Our approach employs multi-criteria density-based clustering, combined with adaptive quality-driven refinement. This method eliminates dependency on external 3D line primitives while ensuring optimal parametric encoding effectiveness. Our comprehensive evaluation across diverse scenes, including both man-made and natural environments, demonstrates that our method achieves up to 1.74 dB improvement in PSNR, 6.7% in SSIM, and 41.4% in LPIPS at equivalent model sizes compared to uniform pruning baselines. For indoor scenes, our method can maintain visual quality with only 0.5\% of the original model size. This structure-aware representation enables efficient storage, adaptive streaming, and rendering of high-fidelity 3D content across bandwidth-constrained networks and resource-limited devices.

Related papers

• A$^2$TG: Adaptive Anisotropic Textured Gaussians for Efficient 3D Scene Representation [7.103085444694659]
  Existing approaches allocate a fixed square texture per primitive, leading to inefficient memory usage and limited adaptability to scene variability.<n>We introduce adaptive anisotropic textured Gaussians (A$2$TG), a novel representation that generalizes textured Gaussians by equipping each primitive with an anisotropic texture.<n>Our method employs a gradient-guided adaptive rule to jointly determine texture resolution and aspect ratio, enabling non-uniform, detail-aware allocation.
  arXiv  Detail & Related papers  (2026-01-14T07:26:55Z)
• Joint Semantic and Rendering Enhancements in 3D Gaussian Modeling with Anisotropic Local Encoding [86.55824709875598]
  We propose a joint enhancement framework for 3D semantic Gaussian modeling that synergizes both semantic and rendering branches.<n>Unlike conventional point cloud shape encoding, we introduce an anisotropic 3D Gaussian Chebyshev descriptor to capture fine-grained 3D shape details.<n>We employ a cross-scene knowledge transfer module to continuously update learned shape patterns, enabling faster convergence and robust representations.
  arXiv  Detail & Related papers  (2026-01-05T18:33:50Z)
• DensifyBeforehand: LiDAR-assisted Content-aware Densification for Efficient and Quality 3D Gaussian Splatting [1.5576275034099496]
  This paper addresses the limitations of existing 3D Gaussian Splatting (3DGS) methods by combining sparse LiDAR data with monocular depth estimation from corresponding RGB images.<n>Our ROI-aware sampling scheme prioritizes semantically and geometrically important regions, yielding a dense point cloud.<n>Our method achieves comparable results to state-of-the-art techniques while significantly lowering resource consumption and training time.
  arXiv  Detail & Related papers  (2025-11-24T16:39:13Z)
• GauSSmart: Enhanced 3D Reconstruction through 2D Foundation Models and Geometric Filtering [50.675710727721786]
  We propose GauSSmart, a hybrid method that bridges 2D foundational models and 3D Gaussian Splatting reconstruction.<n>Our approach integrates established 2D computer vision techniques, including convex filtering and semantic feature supervision.<n>We validate our approach across three datasets, where GauSSmart consistently outperforms existing Gaussian Splatting.
  arXiv  Detail & Related papers  (2025-10-16T03:38:26Z)
• GDGS: 3D Gaussian Splatting Via Geometry-Guided Initialization And Dynamic Density Control [6.91367883100748]
  Gaussian Splatting is an alternative for rendering realistic images while supporting real-time performance.<n>We propose a method to enhance 3D Gaussian Splatting (3DGS)citeKerbl2023, addressing challenges in initialization, optimization, and density control.<n>Our method demonstrates comparable or superior results to state-of-the-art methods, rendering high-fidelity images in real time.
  arXiv  Detail & Related papers  (2025-07-01T01:29:31Z)
• 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)
• LinPrim: Linear Primitives for Differentiable Volumetric Rendering [51.56484100374058]
  We introduce two new scene representations based on linear primitives.<n>We present a different octaiableizer that runs efficiently on GPU.<n>We demonstrate comparable performance to state-of-the-art methods.
  arXiv  Detail & Related papers  (2025-01-27T18:49:38Z)
• Sketch and Patch: Efficient 3D Gaussian Representation for Man-Made Scenes [3.9241077704550777]
  3D Gaussian Splatting has emerged as a promising representation for rendering of 3D scenes.<n>We observe that Gaussians exhibit distinct roles and characteristics that are analogous to traditional artistic techniques.<n>We propose a novel hybrid representation that categorizes Gaussians into (i) Sketch Gaussians, which define scene boundaries, and (ii) Patch Gaussians, which cover smooth regions.
  arXiv  Detail & Related papers  (2025-01-22T17:52:45Z)
• 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)
• Hybrid Explicit Representation for Ultra-Realistic Head Avatars [55.829497543262214]
  We introduce a novel approach to creating ultra-realistic head avatars and rendering them in real-time.<n> UV-mapped 3D mesh is utilized to capture sharp and rich textures on smooth surfaces, while 3D Gaussian Splatting is employed to represent complex geometric structures.<n>Experiments that our modeled results exceed those of state-of-the-art approaches.
  arXiv  Detail & Related papers  (2024-03-18T04:01:26Z)

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.