MVGSR: Multi-View Consistency Gaussian Splatting for Robust Surface Reconstruction

• URL: http://arxiv.org/abs/2503.08093v2
• Date: Thu, 13 Mar 2025 15:09:06 GMT
• Title: MVGSR: Multi-View Consistency Gaussian Splatting for Robust Surface Reconstruction
• Authors: Chenfeng Hou, Qi Xun Yeo, Mengqi Guo, Yongxin Su, Yanyan Li, Gim Hee Lee,
• Abstract summary: 3D Gaussian Splatting (3DGS) has gained significant attention for its high-quality rendering capabilities, ultra-fast training, and inference speeds.<n>We propose Multi-View Consistency Gaussian Splatting for the domain of Robust Surface Reconstruction (textbfMVGSR)<n>MVGSR achieves competitive geometric accuracy and rendering fidelity compared to the state-of-the-art surface reconstruction algorithms.
• Score: 46.081262181141504
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: 3D Gaussian Splatting (3DGS) has gained significant attention for its high-quality rendering capabilities, ultra-fast training, and inference speeds. However, when we apply 3DGS to surface reconstruction tasks, especially in environments with dynamic objects and distractors, the method suffers from floating artifacts and color errors due to inconsistency from different viewpoints. To address this challenge, we propose Multi-View Consistency Gaussian Splatting for the domain of Robust Surface Reconstruction (\textbf{MVGSR}), which takes advantage of lightweight Gaussian models and a {heuristics-guided distractor masking} strategy for robust surface reconstruction in non-static environments. Compared to existing methods that rely on MLPs for distractor segmentation strategies, our approach separates distractors from static scene elements by comparing multi-view feature consistency, allowing us to obtain precise distractor masks early in training. Furthermore, we introduce a pruning measure based on multi-view contributions to reset transmittance, effectively reducing floating artifacts. Finally, a multi-view consistency loss is applied to achieve high-quality performance in surface reconstruction tasks. Experimental results demonstrate that MVGSR achieves competitive geometric accuracy and rendering fidelity compared to the state-of-the-art surface reconstruction algorithms. More information is available on our project page (https://mvgsr.github.io).

Related papers

• GS-I$^{3}$: Gaussian Splatting for Surface Reconstruction from Illumination-Inconsistent Images [6.055104738156626]
  3D Gaussian Splatting (3DGS) has gained significant attention in the field of surface reconstruction. We propose a method called GS-3I to address the challenge of robust surface reconstruction under inconsistent illumination. We show that GS-3I can achieve robust and accurate surface reconstruction across complex illumination scenarios.
  arXiv  Detail & Related papers  (2025-03-16T03:08:54Z)
• 3D Gaussian Splatting with Normal Information for Mesh Extraction and Improved Rendering [8.59572577251833]
  We propose a novel regularization method using the gradients of a signed distance function estimated from the Gaussians.<n>We demonstrate the effectiveness of our approach on datasets such as Mip-NeRF360, Tanks and Temples, and Deep-Blending.
  arXiv  Detail & Related papers  (2025-01-14T18:40:33Z)
• GausSurf: Geometry-Guided 3D Gaussian Splatting for Surface Reconstruction [79.42244344704154]
  GausSurf employs geometry guidance from multi-view consistency in texture-rich areas and normal priors in texture-less areas of a scene.<n>Our method surpasses state-of-the-art methods in terms of reconstruction quality and computation time.
  arXiv  Detail & Related papers  (2024-11-29T03:54:54Z)
• G2SDF: Surface Reconstruction from Explicit Gaussians with Implicit SDFs [84.07233691641193]
  We introduce G2SDF, a novel approach that integrates a neural implicit Signed Distance Field into the Gaussian Splatting framework. G2SDF achieves superior quality than prior works while maintaining the efficiency of 3DGS.
  arXiv  Detail & Related papers  (2024-11-25T20:07:07Z)
• DyGASR: Dynamic Generalized Exponential Splatting with Surface Alignment for Accelerated 3D Mesh Reconstruction [1.2891210250935148]
  We propose DyGASR, which utilizes generalized exponential function instead of traditional 3D Gaussian to decrease the number of particles. We also introduce Generalized Surface Regularization (GSR), which reduces the smallest scaling vector of each point cloud to zero. Our approach surpasses existing 3DGS-based mesh reconstruction methods, demonstrating a 25% increase in speed, and a 30% reduction in memory usage.
  arXiv  Detail & Related papers  (2024-11-14T03:19:57Z)
• GUS-IR: Gaussian Splatting with Unified Shading for Inverse Rendering [83.69136534797686]
  We present GUS-IR, a novel framework designed to address the inverse rendering problem for complicated scenes featuring rough and glossy surfaces. This paper starts by analyzing and comparing two prominent shading techniques popularly used for inverse rendering, forward shading and deferred shading. We propose a unified shading solution that combines the advantages of both techniques for better decomposition.
  arXiv  Detail & Related papers  (2024-11-12T01:51:05Z)
• MCGS: Multiview Consistency Enhancement for Sparse-View 3D Gaussian Radiance Fields [73.49548565633123]
  Radiance fields represented by 3D Gaussians excel at synthesizing novel views, offering both high training efficiency and fast rendering. Existing methods often incorporate depth priors from dense estimation networks but overlook the inherent multi-view consistency in input images. We propose a view framework based on 3D Gaussian Splatting, named MCGS, enabling scene reconstruction from sparse input views.
  arXiv  Detail & Related papers  (2024-10-15T08:39:05Z)
• TranSplat: Generalizable 3D Gaussian Splatting from Sparse Multi-View Images with Transformers [14.708092244093665]
  We develop a strategy that utilizes a predicted depth confidence map to guide accurate local feature matching. We present a novel G-3DGS method named TranSplat, which obtains the best performance on both the RealEstate10K and ACID benchmarks.
  arXiv  Detail & Related papers  (2024-08-25T08:37:57Z)
• SMORE: Simulataneous Map and Object REconstruction [66.66729715211642]
  We present a method for dynamic surface reconstruction of large-scale urban scenes from LiDAR.<n>We take a holistic perspective and optimize a compositional model of a dynamic scene that decomposes the world into rigidly-moving objects and the background.
  arXiv  Detail & Related papers  (2024-06-19T23:53:31Z)

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.