IMLS-Splatting: Efficient Mesh Reconstruction from Multi-view Images via Point Representation
Open Access
- 27 July 2025
- journal article
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Graphics
- Vol. 44 (4) , 1-11
Abstract
Multi-view mesh reconstruction has long been a challenging problem in graphics and computer vision. In contrast to recent volumetric rendering methods that generate meshes through post-processing, we propose an end-to-end mesh optimization approach called IMLS-Splatting. Our method leverages the sparsity and flexibility of point clouds to efficiently represent the underlying surface. To achieve this, we introduce a splatting-based differentiable Implicit Moving-Least Squares (IMLS) algorithm that enables the fast conversion of point clouds into SDFs and texture fields, optimizing both mesh reconstruction and rasterization. Additionally, the IMLS representation ensures that the reconstructed SDF and mesh maintain continuity and smoothness without the need for extra regularization. With this efficient pipeline, our method enables the reconstruction of highly detailed meshes in approximately 11 minutes, supporting high-quality rendering and achieving state-of-the-art reconstruction performance. Our code is available at https://github.com/SilenKZYoung/IMLS-Splatting.Keywords
Funding Information
- the Fundamental Research Funds for the Central Universities (WK9100000063)
This publication has 30 references indexed in Scilit:
- Deblurring 3D Gaussian Splatting2024
- SuGaR: Surface-Aligned Gaussian Splatting for Efficient 3D Mesh Reconstruction and High-Quality Mesh Rendering2024
- Compressed 3D Gaussian Splatting for Accelerated Novel View Synthesis2024
- Extracting Triangular 3D Models, Materials, and Lighting From Images2022
- Mip-NeRF 360: Unbounded Anti-Aliased Neural Radiance Fields2022
- Deep Implicit Moving Least-Squares Functions for 3D Reconstruction2021
- NeRF: Representing Scenes as Neural Radiance Fields for View Synthesis2020
- Differentiable Volumetric Rendering: Learning Implicit 3D Representations Without 3D Supervision2020
- SynSin: End-to-End View Synthesis From a Single Image2020
- Large Scale Multi-view Stereopsis Evaluation2014