cs.CVMar 25, 2026

Accurate Point Measurement in 3DGS -- A New Alternative to Traditional Stereoscopic-View Based Measurements

Authors: Deyan Deng, Rongjun Qin

Organizations: Dept. of Civil, Environmental and Geodetic Engineering, The Ohio State University, Columbus OH, US · Dept. of Electrical and Computer Engineering, The Ohio State University, Columbus OH, US

Read PDF
Ask AI
Cite

Copy citation

DOINot available for this paper

Abstract

3D Gaussian Splatting (3DGS) has revolutionized real-time rendering with its state-of-the-art novel view synthesis, but its utility for accurate geometric measurement remains underutilized. Compared to multi-view stereo (MVS) point clouds or meshes, 3DGS rendered views present superior visual quality and completeness. However, current point measurement methods still rely on demanding stereoscopic workstations or direct picking on often-incomplete and inaccurate 3D meshes. As a novel view synthesizer, 3DGS renders exact source views and smoothly interpolates in-between views. This allows users to intuitively pick congruent points across different views while operating 3DGS models. By triangulating these congruent points, one can precisely generate 3D point measurements. This approach mimics traditional stereoscopic measurement but is significantly less demanding: it requires neither a stereo workstation nor specialized operator stereoscopic capability. Furthermore, it enables multi-view intersection (more than two views) for higher measurement accuracy. We implemented a web-based application to demonstrate this proof-of-concept (PoC). Using several UAV aerial datasets, we show this PoC allows users to successfully perform highly accurate point measurements, achieving accuracy matching or exceeding traditional stereoscopic methods on standard hardware. Specifically, our approach significantly outperforms direct mesh-based measurements. Quantitatively, our method achieves RMSEs in the 1-2 cm range on well-defined points. More critically, on challenging thin structures where mesh-based RMSE was 0.062 m, our method achieved 0.037 m. On sharp corners poorly reconstructed in the mesh, our method successfully measured all points with a 0.013 m RMSE, whereas the mesh method failed entirely. Code is available at: https://github.com/GDAOSU/3dgs_measurement_tool.

Figures & tables

Figure 1: User interface of the web-based measurement application. The panel (left) lists the computed 3D points and their corresponding RMS error ( σ\sigma ). In the 3D view, multiple user-aimed rays (yellow lines) are used to compute the 3D point via spatial intersection. The final point is visualized as a 3D error ellipsoid (blue/green), providing immediate feedback on the measurement’s precision.
ComponentTechnology & Role
Data StorageAmazon S3. Hosts 3DGS models converted to OGC 3D Tiles.
BackendNode.js / Express.js. Serves the client application and acts as a secure gateway to stream 3D Tiles data from S3.
Web ClientCesium.js / React. Cesium.js provides the core 3DGS rendering, 3D globe, and camera APIs. React manages the UI overlays.
ComputationJavaScript. Implements the client-side least-squares solution (Eq. 6 ) within the client application.
Table 1: System Implementation Architecture
Figure 2: Datasets used for experiments. (a - c): mesh models for Dataset 1 - 3; (d - f): 3DGS models for Datasets 1 - 3.
Figure 3: Ground truth generation in iTwin Capture Modeler [ 2 ] . A single validation point (VP) is precisely measured across multiple source images. The system then computes its 3D coordinate via rigorous spatial intersection, which serves as the high-accuracy ground truth for our validation.
Figure 4: Distribution of the 20 validation points (VPs) used for the accuracy assessment, shown on the 3DGS rendering of the three datasets. (Top Left) Dataset 1: steel sculpture; (Bottom Left) Dataset 2: wood sculpture. (Right) Dataset3: campus building.
DatasetMethodNRMSEMEStd
1 (Steel)Mesh200.0300.0280.015
 Ours200.0220.0220.003
2 (Wood)Mesh200.0340.0330.005
 Ours200.0210.0190.006
3 (Building)Mesh200.0310.0280.024
 Ours200.0190.0140.008
Table 2: Accuracy assessment (in meters) comparing mesh and 3DGS measurements against 20 validation points (VPs) per dataset. ME = Mean Error (Bias), Std = Standard Deviation (Precision).
Figure 5: Visual analysis of measurement feasibility on thin structures (Dataset 1). This table compares measurement attempts on five different thin, pole-like features. The Mesh detail column (Col. 2) shows the mesh geometry, which appears missing or discontinuous for points 4 and 5 (circled in yellow), leading to measurement failure. The 3DGS detail column (Col. 3) shows the visually coherent 3DGS rendering, which enabled successful and precise measurements (indicated by the blue error ellipsoid) for all five points.
Figure 6: Measurement feasibility on sharp corners (Dataset 2). The mesh model (column 2) fails to reconstruct the sharp corners due to poor UAV viewing angles, making measurement impossible (”✗”). The 3DGS rendering (column 3) clearly depicts the corners, enabling successful measurement (”✓”).
More in this topic

Multi-View Geometry

Multi-view geometry studies how images from different viewpoints reveal camera motion, scene structure, and consistent 3D measurements.

See all 97 papers

Explore similar work

CardsList
Aug 1, 2025

PointGauss: Point Cloud-Guided Multi-Object Segmentation for Gaussian Splatting

While 3D Gaussian Splatting (3DGS) has established new standards for high-fidelity 3D scene modeling, interpreting massive, unstructured Gaussian primitives into meaningful geospatial entities remains a critical challenge for remote sensing and urban applications. Existing 2D-to-3D distillation methods suffer from projection ambiguities, geometric inconsistencies, and computational bottlenecks when applied to complex, large-scale topographies. Furthermore, current benchmarks lack natively aligned 2D-3D ground truth tailored for splatting-based representations. To address these limitations, we propose PointGauss, a unified 3D-native framework for robust semantic parsing and instance segmentation. By treating Gaussian primitives as unstructured point sets, PointGauss leverages Point Transformer V3 (PTv3) to extract scale-invariant geometric features directly from Gaussian attributes, effectively resolving projection ambiguities. To ensure scalability in building-scale scenes, we introduce an adaptive region-of-interest cropping strategy and an instance-aware distance-constrained rasterization pipeline for pixel-level, view-consistent projection. Additionally, we present SplatSeg-360, the first rigorous cross-scale benchmark tailored for 3DGS, comprising 32 complex scenes with full 360∘^\circ coverage and over 6,300 natively aligned 2D-3D masks. Extensive experiments demonstrate that PointGauss operates in real-time and achieves state-of-the-art performance. Notably, it attains approximately 90% 3D-mIoU in large-scale building scenarios and roughly 80% 2D-mIoU in view-consistent 2D instance segmentation, outperforming baseline methods by 16%. (Code)

Wentao Sun, Yiping Chen, John S. Zelek +1

University of Waterloo, Waterloo, ON N2L 3G1, Canada · Sun Yat-Sen University, Zhuhai 519082, China

3D Gaussian Splatting3DGS Segmentation3D Semantic SegmentationRemote Sensing3D Instance Segmentation
AskPDF
Jun 29, 2026

StereoGS: Sparse-View 3D Gaussian Splatting via Stereo Priors

3D Gaussian Splatting (3DGS) has achieved remarkable success in real-time novel view synthesis, yet it suffers from severe overfitting under sparse-view settings due to insufficient geometric constraints. While recent methods introduce monocular depth priors to mitigate this, they inherently struggle with scale ambiguity and cross-view inconsistency, leading to defective geometry. In this paper, we propose StereoGS, a novel sparse-view 3DGS framework that integrates stereo priors to establish reliable binocular consistency. Unlike scale-agnostic monocular constraints, StereoGS introduces a Stereo Depth Regularization by constructing virtual stereo pairs during optimization and leveraging a foundation stereo model to enforce absolute scale and binocular-consistent structures. To further suppress overfitting and eliminate redundant primitives, we design a Gradient-Aware Opacity Decay strategy that dynamically penalizes Gaussians based on their relative opacity gradient magnitudes. Combined with a Consistency-Aware Dense Initialization using zero-shot multi-view depth estimation, StereoGS effectively anchors primitives to accurate scene surfaces. Extensive experiments on LLFF, DTU, Mip-NeRF360, and Blender datasets demonstrate that StereoGS achieves state-of-the-art performance in sparse-view settings without incurring any additional inference overhead. Project Page: https://stringerywh00.github.io/StereoGS_project_page/

Wenhao Yuan, Yiyuan Ge, Deli Cai

South China University of Technology, China

Multi-View Consistency3D Gaussian SplattingSparse-View 3D Reconstruction
AskPDF
Jun 20, 2026

Mesh2GS: White-Box 3DGS Construction via Plenoptic Sampling

3D Gaussian Splatting (3DGS) has emerged as a promising method for high-quality, real-time 3D reconstruction. To associate 3DGS with mesh representations, existing methods primarily focus on 3DGS-to-mesh reconstruction from multi-view images. In contrast, the problem of converting a mesh into 3DGS has received comparatively less attention. Instead of relying on heuristic strategies that bind 3D Gaussians to the mesh, we propose a novel white-box 3DGS construction framework, termed Mesh2GS, which generates 3DGS directly from mesh geometry based on plenoptic sampling theory, achieving Nyquist-level performance for high-quality global illumination rendering. Firstly, we propose a plenoptic sampling guided 3DGS construction strategy that theoretically derives the minimum sampling rate of the sampled views and the distribution of 3D Gaussians. Second, we propose a novel 3DGS update procedure with albedo--shading decomposition for efficient global-illumination capture. Finally, we introduce a neural illumination enhancement module to handle non-Lambertian effects. Experimental results demonstrate that our method surpasses state-of-the-art baselines and is practically effective for both real-time shared rendering and non-Lambertian effects capturing specular highlights. The project code will be released upon acceptance.

Haoran Zhu, Youcheng Cai, Huangsheng Du +2

University of Science and Technology of China

3D Gaussian SplattingLanguage-Embedded 3DGS
AskPDF