TSPE-GS: Probabilistic Depth Extraction for Semi-Transparent Surface Reconstruction via 3D Gaussian Splatting

• URL: http://arxiv.org/abs/2511.09944v1
• Date: Fri, 14 Nov 2025 01:20:21 GMT
• Title: TSPE-GS: Probabilistic Depth Extraction for Semi-Transparent Surface Reconstruction via 3D Gaussian Splatting
• Authors: Zhiyuan Xu, Nan Min, Yuhang Guo, Tong Wei,
• Abstract summary: 3D Gaussian Splatting offers a strong speed-quality trade-off but struggles to reconstruct semi-transparent surfaces because most methods assume a single depth per pixel.<n>We propose TSPE-GS, which uniformly samples transmittance to model a pixel-wise multi-modal distribution of opacity and depth.
• Score: 15.513430559997701
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: 3D Gaussian Splatting offers a strong speed-quality trade-off but struggles to reconstruct semi-transparent surfaces because most methods assume a single depth per pixel, which fails when multiple surfaces are visible. We propose TSPE-GS (Transparent Surface Probabilistic Extraction for Gaussian Splatting), which uniformly samples transmittance to model a pixel-wise multi-modal distribution of opacity and depth, replacing the prior single-peak assumption and resolving cross-surface depth ambiguity. By progressively fusing truncated signed distance functions, TSPE-GS reconstructs external and internal surfaces separately within a unified framework. The method generalizes to other Gaussian-based reconstruction pipelines without extra training overhead. Extensive experiments on public and self-collected semi-transparent and opaque datasets show TSPE-GS significantly improves semi-transparent geometry reconstruction while maintaining performance on opaque scenes.

Related papers

• DiffTrans: Differentiable Geometry-Materials Decomposition for Reconstructing Transparent Objects [53.83670041249326]
  Reconstructing transparent objects from a set of multi-view images is a challenging task due to the complicated nature and indeterminate behavior of light propagation.<n>We propose a differentiable rendering framework for transparent objects, dubbed DiffTrans, which allows for efficient decomposition and reconstruction of the geometry and materials of transparent objects.
  arXiv  Detail & Related papers  (2026-02-28T02:21:31Z)
• SDFoam: Signed-Distance Foam for explicit surface reconstruction [8.803067028201387]
  We show how to learn an explicit Voronoi Diagram (VD) with an implicit Distance Field (SDF)<n>The resulting model produces crisper, view-consistent surfaces with fewer floaters and improved topology.<n>Across diverse scenes, our hybrid implicit-explicit formulation, which we name SDFoam, substantially improves mesh reconstruction accuracy (Chamfer distance) with comparable appearance (PSNR, SSIM)
  arXiv  Detail & Related papers  (2025-12-18T16:11:18Z)
• PFDepth: Heterogeneous Pinhole-Fisheye Joint Depth Estimation via Distortion-aware Gaussian-Splatted Volumetric Fusion [61.6340987158734]
  We present the first pinhole-fisheye framework for heterogeneous multi-view depth estimation, PFDepth.<n> PFDepth employs a unified architecture capable of processing arbitrary combinations of pinhole and fisheye cameras with varied intrinsics and extrinsics.<n>We show that PFDepth sets a state-of-the-art performance on KITTI-360 and RealHet datasets over current mainstream depth networks.
  arXiv  Detail & Related papers  (2025-09-30T09:38:59Z)
• MILo: Mesh-In-the-Loop Gaussian Splatting for Detailed and Efficient Surface Reconstruction [38.02000636240954]
  We present MILo, a novel framework that bridges the gap between volumetric and surface representations by differentiably extracting a mesh from the 3D Gaussians.<n>Our approach can reconstruct complete scenes, including backgrounds, with state-of-the-art quality while requiring an order of magnitude fewer mesh vertices than previous methods.
  arXiv  Detail & Related papers  (2025-06-30T17:48:54Z)
• TSGS: Improving Gaussian Splatting for Transparent Surface Reconstruction via Normal and De-lighting Priors [39.60777069381983]
  We introduce Transparent Surface Gaussian Splatting (TSGS), a new framework that separates geometry learning from appearance refinement.<n>In the geometry learning stage, TSGS focuses on geometry by using specular-suppressed inputs to accurately represent surfaces.<n>To enhance depth inference, TSGS employs a first-surface depth extraction method.
  arXiv  Detail & Related papers  (2025-04-17T10:00:09Z)
• TranSplat: Surface Embedding-guided 3D Gaussian Splatting for Transparent Object Manipulation [10.957451368533302]
  TranSplat is a surface embedding-guided 3D Gaussian Splatting method tailored for transparent objects.<n>By integrating these surface embeddings with input RGB images, TranSplat effectively captures the complexities of transparent surfaces.
  arXiv  Detail & Related papers  (2025-02-11T03:43:56Z)
• GLS: Geometry-aware 3D Language Gaussian Splatting [16.578191875763178]
  This paper presents a unified framework of 3D surface reconstruction and open-vocabulary segmentation based on 3DGS.<n>For indoor surface reconstruction, we introduce surface normal prior as a geometric cue to guide the rendered normal, and use the normal error to optimize the rendered depth.<n>For 3D open-vocabulary segmentation, we employ 2D CLIP features to guide instance features and enhance the surface smoothness, then utilize DEVA masks to maintain their view consistency.
  arXiv  Detail & Related papers  (2024-11-27T05:21:34Z)
• MonoGSDF: Exploring Monocular Geometric Cues for Gaussian Splatting-Guided Implicit Surface Reconstruction [86.87464903285208]
  We introduce MonoGSDF, a novel method that couples primitives with a neural Signed Distance Field (SDF) for high-quality reconstruction.<n>To handle arbitrary-scale scenes, we propose a scaling strategy for robust generalization.<n>Experiments on real-world datasets outperforms prior methods while maintaining efficiency.
  arXiv  Detail & Related papers  (2024-11-25T20:07:07Z)
• Volumetric Surfaces: Representing Fuzzy Geometries with Layered Meshes [59.17785932398617]
  High-quality view synthesis relies on volume rendering, splatting, or surface rendering.<n>We present a novel representation for real-time view synthesis where the number of sampling locations is small and bounded.<n>We achieve this by representing objects as semi-transparent multi-layer meshes rendered in a fixed order.
  arXiv  Detail & Related papers  (2024-09-04T07:18:26Z)
• Binary Opacity Grids: Capturing Fine Geometric Detail for Mesh-Based View Synthesis [70.40950409274312]
  We modify density fields to encourage them to converge towards surfaces, without compromising their ability to reconstruct thin structures. We also develop a fusion-based meshing strategy followed by mesh simplification and appearance model fitting. The compact meshes produced by our model can be rendered in real-time on mobile devices.
  arXiv  Detail & Related papers  (2024-02-19T18:59:41Z)
• NeuSD: Surface Completion with Multi-View Text-to-Image Diffusion [56.98287481620215]
  We present a novel method for 3D surface reconstruction from multiple images where only a part of the object of interest is captured. Our approach builds on two recent developments: surface reconstruction using neural radiance fields for the reconstruction of the visible parts of the surface, and guidance of pre-trained 2D diffusion models in the form of Score Distillation Sampling (SDS) to complete the shape in unobserved regions in a plausible manner.
  arXiv  Detail & Related papers  (2023-12-07T19:30:55Z)

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.