Deformable Beta Splatting
- URL: http://arxiv.org/abs/2501.18630v1
- Date: Mon, 27 Jan 2025 18:58:43 GMT
- Title: Deformable Beta Splatting
- Authors: Rong Liu, Dylan Sun, Meida Chen, Yue Wang, Andrew Feng,
- Abstract summary: 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.
- Score: 4.855751031707892
- License:
- Abstract: 3D Gaussian Splatting (3DGS) has advanced radiance field reconstruction by enabling real-time rendering. However, its reliance on Gaussian kernels for geometry and low-order Spherical Harmonics (SH) for color encoding limits its ability to capture complex geometries and diverse colors. We introduce Deformable Beta Splatting (DBS), a deformable and compact approach that enhances both geometry and color representation. DBS replaces Gaussian kernels with deformable Beta Kernels, which offer bounded support and adaptive frequency control to capture fine geometric details with higher fidelity while achieving better memory efficiency. In addition, we extended the Beta Kernel to color encoding, which facilitates improved representation of diffuse and specular components, yielding superior results compared to SH-based methods. Furthermore, Unlike prior densification techniques that depend on Gaussian properties, we mathematically prove that adjusting regularized opacity alone ensures distribution-preserved Markov chain Monte Carlo (MCMC), independent of the splatting kernel type. Experimental results demonstrate that DBS achieves state-of-the-art visual quality while utilizing only 45% of the parameters and rendering 1.5x faster than 3DGS-based methods. Notably, for the first time, splatting-based methods outperform state-of-the-art Neural Radiance Fields, highlighting the superior performance and efficiency of DBS for real-time radiance field rendering.
Related papers
- SG-Splatting: Accelerating 3D Gaussian Splatting with Spherical Gaussians [21.00454010373162]
3D Gaussian Splatting is emerging as a state-of-the-art technique in novel view synthesis.
However, reliance on third-degree spherical harmonics for color representation introduces significant storage demands and computational overhead.
We introduce SG-Splatting with Spherical Gaussians based color representation, a novel approach to enhance rendering speed and quality.
arXiv Detail & Related papers (2024-12-31T08:31:52Z) - Deformable Radial Kernel Splatting [53.92593804734493]
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.
arXiv Detail & Related papers (2024-12-16T13:11:02Z) - SuperGaussians: Enhancing Gaussian Splatting Using Primitives with Spatially Varying Colors [51.54964131894217]
We introduce a new method called SuperGaussians that utilizes spatially varying colors and opacity in a single Gaussian primitive to improve its representation ability.
We have implemented bilinear, movable kernels, and even tiny neural networks as spatially varying functions.
arXiv Detail & Related papers (2024-11-28T07:36:22Z) - 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) - RayGauss: Volumetric Gaussian-Based Ray Casting for Photorealistic Novel View Synthesis [3.4341938551046227]
Differentiable rendering methods made significant progress in novel view synthesis.
We provide a consistent formulation of the emitted radiance c and density sigma for differentiable ray casting of irregularly distributed Gaussians.
We achieve superior quality rendering compared to the state-of-the-art while maintaining reasonable training times and achieving inference speeds of 25 FPS on the Blender dataset.
arXiv Detail & Related papers (2024-08-06T10:59:58Z) - Textured-GS: Gaussian Splatting with Spatially Defined Color and Opacity [7.861993966048637]
We introduce Textured-GS, an innovative method for rendering Gaussian splatting using Spherical Harmonics (SH)
This approach enables each Gaussian to exhibit a richer representation by accommodating varying colors and opacities across its surface.
Our experiments show that Textured-GS consistently outperforms both the baseline Mini-Splatting and standard 3DGS in terms of visual fidelity.
arXiv Detail & Related papers (2024-07-13T00:45:37Z) - 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) - GaussianPro: 3D Gaussian Splatting with Progressive Propagation [49.918797726059545]
3DGS relies heavily on the point cloud produced by Structure-from-Motion (SfM) techniques.
We propose a novel method that applies a progressive propagation strategy to guide the densification of the 3D Gaussians.
Our method significantly surpasses 3DGS on the dataset, exhibiting an improvement of 1.15dB in terms of PSNR.
arXiv Detail & Related papers (2024-02-22T16:00:20Z) - Feature 3DGS: Supercharging 3D Gaussian Splatting to Enable Distilled Feature Fields [54.482261428543985]
Methods that use Neural Radiance fields are versatile for traditional tasks such as novel view synthesis.
3D Gaussian splatting has shown state-of-the-art performance on real-time radiance field rendering.
We propose architectural and training changes to efficiently avert this problem.
arXiv Detail & Related papers (2023-12-06T00:46:30Z)
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.