Deformable Radial Kernel Splatting

• URL: http://arxiv.org/abs/2412.11752v1
• Date: Mon, 16 Dec 2024 13:11:02 GMT
• Title: Deformable Radial Kernel Splatting
• Authors: Yi-Hua Huang, Ming-Xian Lin, Yang-Tian Sun, Ziyi Yang, Xiaoyang Lyu, Yan-Pei Cao, Xiaojuan Qi,
• Abstract summary: We introduce Deformable Radial Kernel (DRK), which extends Gaussian splatting into a more general and flexible framework. DRK efficiently models diverse shape primitives while enabling precise control over edge sharpness and boundary curvature.
• Score: 53.92593804734493
• License:
• Abstract: Recently, Gaussian splatting has emerged as a robust technique for representing 3D scenes, enabling real-time rasterization and high-fidelity rendering. However, Gaussians' inherent radial symmetry and smoothness constraints limit their ability to represent complex shapes, often requiring thousands of primitives to approximate detailed geometry. We introduce Deformable Radial Kernel (DRK), which extends Gaussian splatting into a more general and flexible framework. Through learnable radial bases with adjustable angles and scales, DRK efficiently models diverse shape primitives while enabling precise control over edge sharpness and boundary curvature. iven DRK's planar nature, we further develop accurate ray-primitive intersection computation for depth sorting and introduce efficient kernel culling strategies for improved rasterization efficiency. Extensive experiments demonstrate that DRK outperforms existing methods in both representation efficiency and rendering quality, achieving state-of-the-art performance while dramatically reducing primitive count.

Related papers

• Deformable Beta Splatting [4.855751031707892]
  3D Gaussian Splatting (3DGS) has advanced radiance field reconstruction by enabling real-time rendering. We introduce Deformable Beta Splatting (DBS), a deformable and compact approach that enhances both geometry and color representation.
  arXiv  Detail & Related papers  (2025-01-27T18:58:43Z)
• Tortho-Gaussian: Splatting True Digital Orthophoto Maps [12.796166971391774]
  True Digital Orthophoto Maps (TDOMs) are essential products for digital twins and Geographic Information Systems (GIS) Traditionally, TDOM generation involves a complex set of traditional photogrammetric process, which may deteriorate due to various challenges. We introduce TOrtho-Gaussian, a novel method inspired by 3D Gaussian Splatting (3DGS) that generates TDOMs through splatting of optimized anisotropic Gaussian kernel.
  arXiv  Detail & Related papers  (2024-11-29T10:22:38Z)
• Beyond Gaussians: Fast and High-Fidelity 3D Splatting with Linear Kernels [51.08794269211701]
  We introduce 3D Linear Splatting (3DLS), which replaces Gaussian kernels with linear kernels to achieve sharper and more precise results. 3DLS demonstrates state-of-the-art fidelity and accuracy, along with a 30% FPS improvement over baseline 3DGS.
  arXiv  Detail & Related papers  (2024-11-19T11:59:54Z)
• RaDe-GS: Rasterizing Depth in Gaussian Splatting [32.38730602146176]
  Gaussian Splatting (GS) has proven to be highly effective in novel view synthesis, achieving high-quality and real-time rendering. Our work introduces a Chamfer distance error comparable to NeuraLangelo on the DTU dataset and maintains similar computational efficiency as the original 3D GS methods.
  arXiv  Detail & Related papers  (2024-06-03T15:56:58Z)
• R$^2$-Gaussian: Rectifying Radiative Gaussian Splatting for Tomographic Reconstruction [53.19869886963333]
  3D Gaussian splatting (3DGS) has shown promising results in rendering image and surface reconstruction. This paper introduces R2$-Gaussian, the first 3DGS-based framework for sparse-view tomographic reconstruction.
  arXiv  Detail & Related papers  (2024-05-31T08:39:02Z)
• AtomGS: Atomizing Gaussian Splatting for High-Fidelity Radiance Field [12.025400772749913]
  3D Gaussian Splatting (3DGS) has recently advanced radiance field reconstruction by offering superior capabilities for novel view synthesis and real-time rendering speed. We introduce AtomGS, consisting of Atomized Proliferation and Geometry-Guided Optimization. Our evaluation shows that AtomGS outperforms existing state-of-the-art methods in rendering quality.
  arXiv  Detail & Related papers  (2024-05-20T20:38:22Z)
• Gaussian Opacity Fields: Efficient Adaptive Surface Reconstruction in Unbounded Scenes [50.92217884840301]
  Gaussian Opacity Fields (GOF) is a novel approach for efficient, high-quality, and adaptive surface reconstruction in scenes. GOF is derived from ray-tracing-based volume rendering of 3D Gaussians. GOF surpasses existing 3DGS-based methods in surface reconstruction and novel view synthesis.
  arXiv  Detail & Related papers  (2024-04-16T17:57:19Z)
• 2D Gaussian Splatting for Geometrically Accurate Radiance Fields [50.056790168812114]
  3D Gaussian Splatting (3DGS) has recently revolutionized radiance field reconstruction, achieving high quality novel view synthesis and fast rendering speed without baking. We present 2D Gaussian Splatting (2DGS), a novel approach to model and reconstruct geometrically accurate radiance fields from multi-view images. We demonstrate that our differentiable terms allows for noise-free and detailed geometry reconstruction while maintaining competitive appearance quality, fast training speed, and real-time rendering.
  arXiv  Detail & Related papers  (2024-03-26T17:21:24Z)
• Isotropic Gaussian Splatting for Real-Time Radiance Field Rendering [15.498640737050412]
  The proposed method can be applied in a large range applications, such as 3D reconstruction, view synthesis, and dynamic object modeling. The experiments confirm that the proposed method is about bf 100X faster without losing the geometry representation accuracy.
  arXiv  Detail & Related papers  (2024-03-21T09:02:31Z)
• NeuRBF: A Neural Fields Representation with Adaptive Radial Basis Functions [93.02515761070201]
  We present a novel type of neural fields that uses general radial bases for signal representation. Our method builds upon general radial bases with flexible kernel position and shape, which have higher spatial adaptivity and can more closely fit target signals. When applied to neural radiance field reconstruction, our method achieves state-of-the-art rendering quality, with small model size and comparable training speed.
  arXiv  Detail & Related papers  (2023-09-27T06:32:05Z)

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.