MesoSplats: Texture Synthesis with Gaussian Splatting
- 1 January 2026
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Visualization and Computer Graphics
- Vol. 32 (9) , 1-17
Abstract
Texture is fundamental to high-fidelity rendering of 3D digital assets, directly influencing scene detail and visual real ism. Existing methods typically adopt 2D texture mapping, where texture images are either manually created or synthesized from exemplars. While advances in texture synthesis have improved 2D texture quality, 2D representations remain inadequate for modeling volumetric meso-structure textures with complex geometry. Methods targeting meso-structure textures often struggle to capture high-frequency details and lack real-time rendering capabilities, limiting their practical use. We propose MesoSplats, a neural implicit method for extracting and synthesizing meso structure textures using 3D Gaussian splatting. Given the multi view images containing the meso-structure geometric details, our approach supports texture extraction, synthesis, and real-time rendering. We introduce a mesh-Gaussian hybrid representation that decouples geometry into a coarse base mesh and embedded 3D Gaussians, guided by initial point cloud constraints to enhance reconstruction fidelity. Local implicit texture features are sampled from the base mesh surface and further refined through a proposed Consistency Tuning strategy, which enforces alignment between the reconstruction and sampling spaces. To boost texture synthesis quality, we incorporate a tile ability-aware patch-matching algorithm alongside a smoothness regularization on the latent feature space to ensure spatial coherence. Extensive quantitative and qualitative experiments demonstrate the effectiveness of our method.Keywords
Funding Information
- National Natural Science Foundation of China (62322210)
- Royal Society International Exchanges 2023 Cost Share (IEC\NSFC\233698)
- Beijing Major Science and Technology Project (Z251100008125009)
- Innovation Funding of ICT, CAS (E561100)
- China Postdoctoral Science Foundation (BX20230377)
This publication has 108 references indexed in Scilit:
- GRM: Large Gaussian Reconstruction Model for Efficient 3D Reconstruction and Generation2024
- CityGaussian: Real-Time High-Quality Large-Scale Scene Rendering with Gaussians2024
- Texture-GS: Disentangling the Geometry and Texture for 3D Gaussian Splatting Editing2024
- DreamScene360: Unconstrained Text-to-3D Scene Generation with Panoramic Gaussian Splatting2024
- TensoRF: Tensorial Radiance Fields2022
- NeuMesh: Learning Disentangled Neural Mesh-Based Implicit Field for Geometry and Texture Editing2022
- Neural Point-Based Graphics2020
- Free View Synthesis2020
- NeRF: Representing Scenes as Neural Radiance Fields for View Synthesis2020
- The Phong Surface: Efficient 3D Model Fitting Using Lifted Optimization2020