Geometry Gaussians: Decoupling Appearance and Geometry in Gaussian Splatting

• URL: http://arxiv.org/abs/2606.05124v1
• Date: Wed, 03 Jun 2026 17:29:36 GMT
• Title: Geometry Gaussians: Decoupling Appearance and Geometry in Gaussian Splatting
• Abstract summary: We show that 3DGS in its default form is inheritedly unsuited to represent texture and geometry at the same time.<n>We propose a simple solution by applying a single additional geometry opacity parameter to each splat.
• Score: 28.891336184070223
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: After the success of 3D Gaussian Splatting (3DGS) for novel view synthesis, many works have explored how to also use it for geometric surface representation. However, extracting accurate geometric information directly from 3DGS remains challenging and can often reduce the appearance rendering quality. In this work, we show that 3DGS in its default form is inheritedly unsuited to represent texture and geometry at the same time, by training with complete ground-truth texture and geometry information. We also propose a simple solution by applying a single additional geometry opacity parameter to each splat, together with an optional transparency-curated optimization pipeline. Our experiments, both with ground-truth and vision foundation model geometric input, show that this change leads to improved rendering and geometry performance on a wide variety of dataset, and especially complex scenes with transparent objects benefit significantly from our method.

Related papers

• TV-SGS: Gaussian Splatting with Geometric Information Propagation via Tensor Voting under sparse views [5.274411980510585]
  We introduce a new class of 3D losses that do not rely on rendering and can be combined with essentially all losses previously reported in the literature.<n>Our method is easy to integrate with a diverse set of backbones, and our experiments on the DTU and Tanks-and-Temples datasets demonstrate that TV-SGS improves the geometry of the outputs compared to the backbone.
  arXiv  Detail & Related papers  (2026-09-07T16:40:51Z)
• BrepGaussian: CAD reconstruction from Multi-View Images with Gaussian Splatting [21.289489202626534]
  Boundary representation (B-rep) models a 3D solid as its explicit boundaries.<n>Recent advances in deep learning have greatly improved the recovery of 3D shape geometry.<n>We propose B-rep Splatting, a novel framework that learns 3D parametric representations from 2D images.
  arXiv  Detail & Related papers  (2026-02-24T17:03:45Z)
• UniGS: Unified Geometry-Aware Gaussian Splatting for Multimodal Rendering [10.560500427919647]
  We propose UniGS, a unified map representation and differentiable attribute reconstruction based on 3D Splatting.<n>Our framework integrates a multimodal viewer capable of rendering photo-realistic RGB images, geometrically accurate depth maps, consistent surface normals, and semantic logits simultaneously.
  arXiv  Detail & Related papers  (2025-10-14T06:07:57Z)
• Shape from Semantics: 3D Shape Generation from Multi-View Semantics [30.969299308083723]
  Existing 3D reconstruction methods utilize guidances such as 2D images, 3D point clouds, shape contours and single semantics to recover the 3D surface.<n>We propose a novel 3D modeling task called Shape from Semantics'', which aims to create 3D models whose geometry and appearance are consistent with the given text semantics when viewed from different views.
  arXiv  Detail & Related papers  (2025-02-01T07:51:59Z)
• GeoSplatting: Towards Geometry Guided Gaussian Splatting for Physically-based Inverse Rendering [69.67264955234494]
  GeoSplatting is a novel approach that augments 3DGS with explicit geometry guidance for precise light transport modeling.<n>By differentiably constructing a surface-grounded 3DGS from an optimizable mesh, our approach leverages well-defined mesh normals and the opaque mesh surface.<n>This enhancement ensures precise material decomposition while preserving the efficiency and high-quality rendering capabilities of 3DGS.
  arXiv  Detail & Related papers  (2024-10-31T17:57:07Z)
• GigaGS: Scaling up Planar-Based 3D Gaussians for Large Scene Surface Reconstruction [71.08607897266045]
  3D Gaussian Splatting (3DGS) has shown promising performance in novel view synthesis. We make the first attempt to tackle the challenging task of large-scale scene surface reconstruction. We propose GigaGS, the first work for high-quality surface reconstruction for large-scale scenes using 3DGS.
  arXiv  Detail & Related papers  (2024-09-10T17:51:39Z)
• Direct Learning of Mesh and Appearance via 3D Gaussian Splatting [2.8424636089338216]
  We propose a learnable scene model that incorporates 3DGS with an explicit geometry representation, namely a mesh.<n>Our model learns the mesh and appearance in an end-to-end manner, where we bind 3D Gaussians to the mesh faces and perform differentiable rendering of 3DGS to obtain photometric supervision.
  arXiv  Detail & Related papers  (2024-05-11T07:56:19Z)
• 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)
• 3D Geometry-aware Deformable Gaussian Splatting for Dynamic View Synthesis [49.352765055181436]
  We propose a 3D geometry-aware deformable Gaussian Splatting method for dynamic view synthesis. Our solution achieves 3D geometry-aware deformation modeling, which enables improved dynamic view synthesis and 3D dynamic reconstruction.
  arXiv  Detail & Related papers  (2024-04-09T12:47:30Z)
• Geometry-Contrastive Transformer for Generalized 3D Pose Transfer [95.56457218144983]
  The intuition of this work is to perceive the geometric inconsistency between the given meshes with the powerful self-attention mechanism. We propose a novel geometry-contrastive Transformer that has an efficient 3D structured perceiving ability to the global geometric inconsistencies. We present a latent isometric regularization module together with a novel semi-synthesized dataset for the cross-dataset 3D pose transfer task.
  arXiv  Detail & Related papers  (2021-12-14T13:14:24Z)
• Pix2Surf: Learning Parametric 3D Surface Models of Objects from Images [64.53227129573293]
  We investigate the problem of learning to generate 3D parametric surface representations for novel object instances, as seen from one or more views. We design neural networks capable of generating high-quality parametric 3D surfaces which are consistent between views. Our method is supervised and trained on a public dataset of shapes from common object categories.
  arXiv  Detail & Related papers  (2020-08-18T06:33:40Z)

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.