UniMGS: Unifying Mesh and 3D Gaussian Splatting with Single-Pass Rasterization and Proxy-Based Deformation
Zeyu Xiao, Mingyang Sun, Yimin Cong, Lintao Wang, Dongliang Kou, Zhenyi Wu, Dingkang Yang, Peng Zhai, Zeyu Wang, Lihua Zhang
摘要
Joint rendering and deformation of mesh and 3D Gaussian Splatting (3DGS) have significant value as both representations offer complementary advantages for graphics applications. However, due to differences in representation and rendering pipelines, existing studies render meshes and 3DGS separately, making it difficult to accurately handle occlusions and transparency. Moreover, the deformed 3DGS still suffers from visual artifacts due to the sensitivity to the topology quality of the proxy mesh. These issues pose serious obstacles to the joint use of 3DGS and meshes, making it difficult to adapt 3DGS to conventional mesh-oriented graphics pipelines. We propose UniMGS, the first unified framework for rasterizing mesh and 3DGS in a single-pass anti-aliased manner, with a novel binding strategy for 3DGS deformation based on proxy mesh. Our key insight is to blend the colors of both triangle and Gaussian fragments by anti-aliased α-blending in a single pass, achieving visually coherent results with precise handling of occlusion and transparency. To improve the visual appearance of the deformed 3DGS, our Gaussian-centric binding strategy employs a proxy mesh and spatially associates Gaussians with the mesh faces, significantly reducing rendering artifacts. With these two components, UniMGS enables the visualization and manipulation of 3D objects represented by mesh or 3DGS within a unified framework, opening up new possibilities in embodied AI, virtual reality, and gaming. We will release our source code to facilitate future research.
问问这篇 Paper
智能体会读完全文。
Lune 把这篇 Paper 索引到了每一个公式,引用它的顶会 Paper 也一样。你提问,回答直接引用原文。
它引用的顶会 Paper11
- 3D Gaussian Splatting for Real-Time Radiance Field RenderingBernhard Kerbl, Georgios Kopanas, Thomas Leimkühler, George DrettakisSIGGRAPH 2023 · 被引用 5,687 次
- Mip-NeRF 360: Unbounded Anti-Aliased Neural Radiance FieldsJonathan T. Barron, Ben Mildenhall, Dor Verbin, Pratul P. Srinivasan 等CVPR 2022 · 被引用 1,603 次
- NeuS2: Fast Learning of Neural Implicit Surfaces for Multi-view ReconstructionYiming Wang, Qin Han, Marc Habermann, Kostas Daniilidis 等ICCV 2023 · 被引用 402 次
- PhysGaussian: Physics-Integrated 3D Gaussians for Generative DynamicsTianyi Xie, Zeshun Zong, Yuxing Qiu, Xuan Li 等CVPR 2024 · 被引用 118 次
- Dynamic Mesh-Aware Radiance FieldsYi-Ling Qiao, Alexander Gao, Yiran Xu, Yue Feng 等ICCV 2023 · 被引用 32 次
相关 Paper
- AAA-Gaussians: Anti-Aliased and Artifact-Free 3D Gaussian RenderingMichael Steiner, Thomas Köhler, Lukas Radl, Felix Windisch 等ICCV 2025 · 被引用 5 次
- Hardware-Rasterized Ray-Based Gaussian SplattingSamuel Rota Bulò, Nemanja Bartolovic, Lorenzo Porzi, Peter KontschiederCVPR 2025
- VRGaussianAvatar: Integrating 3D Gaussian Avatars into VRHail Song, Boram Yoon, Seokhwan Yang, Seoyoung Kang 等IEEE VR 2026 · 被引用 2 次
- SplattingAvatar: Realistic Real-Time Human Avatars With Mesh-Embedded Gaussian SplattingZhijing Shao, Zhaolong Wang, Zhuang Li, Duotun Wang 等CVPR 2024 · 被引用 92 次
- DirectTriGS: Triplane-based Gaussian Splatting Field Representation for 3D GenerationXiaoliang Ju, Hongsheng LiCVPR 2025
