SuperGaussians: Enhancing Gaussian Splatting Using Primitives with Spatially Varying Colors

• URL: http://arxiv.org/abs/2411.18966v1
• Date: Thu, 28 Nov 2024 07:36:22 GMT
• Title: SuperGaussians: Enhancing Gaussian Splatting Using Primitives with Spatially Varying Colors
• Authors: Rui Xu, Wenyue Chen, Jiepeng Wang, Yuan Liu, Peng Wang, Lin Gao, Shiqing Xin, Taku Komura, Xin Li, Wenping Wang,
• Abstract summary: We introduce a new method called SuperGaussians that utilizes spatially varying colors and opacity in a single Gaussian primitive to improve its representation ability.<n>We have implemented bilinear, movable kernels, and even tiny neural networks as spatially varying functions.
• Score: 51.54964131894217
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: Gaussian Splattings demonstrate impressive results in multi-view reconstruction based on Gaussian explicit representations. However, the current Gaussian primitives only have a single view-dependent color and an opacity to represent the appearance and geometry of the scene, resulting in a non-compact representation. In this paper, 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 interpolation, movable kernels, and even tiny neural networks as spatially varying functions. Quantitative and qualitative experimental results demonstrate that all three functions outperform the baseline, with the best movable kernels achieving superior novel view synthesis performance on multiple datasets, highlighting the strong potential of spatially varying functions.

Related papers

• ProtoGS: Efficient and High-Quality Rendering with 3D Gaussian Prototypes [81.48624894781257]
  3D Gaussian Splatting (3DGS) has made significant strides in novel view synthesis but is limited by the substantial number of Gaussian primitives required. Recent methods address this issue by compressing the storage size of densified Gaussians, yet fail to preserve rendering quality and efficiency. We propose ProtoGS to learn Gaussian prototypes to represent Gaussian primitives, significantly reducing the total Gaussian amount without sacrificing visual quality.
  arXiv  Detail & Related papers  (2025-03-21T18:55:14Z)
• EigenGS Representation: From Eigenspace to Gaussian Image Space [20.454762899389358]
  EigenGS is an efficient transformation pipeline connecting eigenspace and image-space Gaussian representations. We show that EigenGS achieves superior reconstruction quality compared to direct 2D Gaussian fitting. The results highlight EigenGS's effectiveness and generalization ability across images with varying resolutions and diverse categories.
  arXiv  Detail & Related papers  (2025-03-10T15:27:03Z)
• LinPrim: Linear Primitives for Differentiable Volumetric Rendering [53.780682194322225]
  We introduce two new scene representations based on linear primitives. We present a different octaiableizer that runs efficiently on GPU. We demonstrate comparable performance to state-of-the-art methods.
  arXiv  Detail & Related papers  (2025-01-27T18:49:38Z)
• SmileSplat: Generalizable Gaussian Splats for Unconstrained Sparse Images [91.28365943547703]
  A novel generalizable Gaussian Splatting method, SmileSplat, is proposed to reconstruct pixel-aligned Gaussian surfels for diverse scenarios. The proposed method achieves state-of-the-art performance in various 3D vision tasks.
  arXiv  Detail & Related papers  (2024-11-27T05:52:28Z)
• Geometric Algebra Planes: Convex Implicit Neural Volumes [70.12234371845445]
  We show that GA-Planes is equivalent to a sparse low-rank factor plus low-resolution matrix. We also show that GA-Planes can be adapted for many existing representations.
  arXiv  Detail & Related papers  (2024-11-20T18:21:58Z)
• DiffGS: Functional Gaussian Splatting Diffusion [33.07847512591061]
  3D Gaussian Splatting (3DGS) has shown convincing performance in rendering speed and fidelity. However, the generation of Gaussian Splatting remains a challenge due to its discreteness and unstructured nature. We propose DiffGS, a general Gaussian generator based on latent diffusion models.
  arXiv  Detail & Related papers  (2024-10-25T16:08:08Z)
• PixelGaussian: Generalizable 3D Gaussian Reconstruction from Arbitrary Views [116.10577967146762]
  PixelGaussian is an efficient framework for learning generalizable 3D Gaussian reconstruction from arbitrary views. Our method achieves state-of-the-art performance with good generalization to various numbers of views.
  arXiv  Detail & Related papers  (2024-10-24T17:59:58Z)
• 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)
• RT-GS2: Real-Time Generalizable Semantic Segmentation for 3D Gaussian Representations of Radiance Fields [6.071025178912125]
  We introduce RT-GS2, the first generalizable semantic segmentation method employing Gaussian Splatting. Our method achieves real-time performance of 27.03 FPS, marking an astonishing 901 times speedup compared to existing approaches.
  arXiv  Detail & Related papers  (2024-05-28T10:34:28Z)
• GaussianCube: A Structured and Explicit Radiance Representation for 3D Generative Modeling [55.05713977022407]
  We introduce a radiance representation that is both structured and fully explicit and thus greatly facilitates 3D generative modeling. We derive GaussianCube by first using a novel densification-constrained Gaussian fitting algorithm, which yields high-accuracy fitting. Experiments conducted on unconditional and class-conditioned object generation, digital avatar creation, and text-to-3D all show that our model synthesis achieves state-of-the-art generation results.
  arXiv  Detail & Related papers  (2024-03-28T17:59:50Z)
• Mini-Splatting: Representing Scenes with a Constrained Number of Gaussians [4.733612131945549]
  In this study, we explore the challenge of efficiently representing scenes with a constrained number of Gaussians. We introduce strategies for densification including blur split and depth reinitialization, and simplification through intersection preserving and sampling. Our Mini-Splatting integrates seamlessly with the originalization pipeline, providing a strong baseline for future research in Gaussian-Splatting-based works.
  arXiv  Detail & Related papers  (2024-03-21T06:34:46Z)

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.