Differentiable Micro-Mesh Construction
Yishun Dou, Zhong Zheng, Qiaoqiao Jin, Rui Shi, Yuhan Li, Bingbing Ni
Abstract
Micro-mesh (µ-mesh) is a new graphics primitive for compact representation of extreme geometry, consisting of a low-polygon base mesh enriched by per micro-vertex displacement. A new generation of GPUs supports this structure with hardware evolution on µ-mesh ray tracing, achieving real-time rendering in pixel level geometric details. In this article, we present a differentiable framework to convert standard meshes into this efficient format, offering a holistic scheme in contrast to the previous stage-based methods. In our construction context, a µ-mesh is defined where each base triangle is a parametric primitive, which is then reparameterized with Laplacian operators for efficient geometry optimization. Our framework offers numerous advantages for high-quality µ-mesh production: (i) end-toend geometry optimization and displacement baking; (ii) enabling the differentiation of renderings with respect to µmesh for faithful reprojectability; (iii) high scalability for integrating useful features for µ-mesh production and rendering, such as minimizing shell volume, maintaining the isotropy of the base mesh, and visual-guided adaptive level of detail. Extensive experiments on µ-mesh construction for a large set of high-resolution meshes demonstrate the superior quality achieved by the proposed scheme.
Ask about this paper
Your agent reads all of it.
Lune indexed this paper to the last equation, along with the top-tier papers that cite it. Ask a question and the answer quotes them.
Your agent calls
Luneget_paper_fulltext
Free to start. No credit card required.
Terminal
Install the CLIlune papers fulltext ee8b8744-b884-4dac-be64-62a6c795dedfCited by top-tier papers3
- ExMesh: EXplicit Mesh Reconstruction with Topology AdaptationChuanjin Fan, Lifan Wu, Wenjie Chang, Hanzhi Chang et al.CVPR 2026 · 2 citations
- DJM: Compact Base Meshes for Displacement Mapping using Triangle JacobiansCongyi Zhang, Nicholas Vining, Yanhong Lin, Alireza Khatami et al.SIGGRAPH 2026
- Deep Inverse Shading: Consistent Albedo and Surface Detail Recovery via Generative RefinementJiacheng Wu, Ruiqi Zhang, Jie ChenAAAI 2026
Builds on17
- High-Resolution Image Synthesis with Latent Diffusion ModelsRobin Rombach, Andreas Blattmann, Dominik Lorenz, Patrick Esser et al.CVPR 2022 · 13,123 citations
- 3D Gaussian Splatting for Real-Time Radiance Field RenderingBernhard Kerbl, Georgios Kopanas, Thomas Leimkühler, George DrettakisSIGGRAPH 2023 · 5,687 citations
- Instant neural graphics primitives with a multiresolution hash encodingThomas Müller, Alex Evans, Christoph Schied, Alexander KellerSIGGRAPH 2022 · 4,089 citations
- Fantasia3D: Disentangling Geometry and Appearance for High-quality Text-to-3D Content CreationRui Chen, Yongwei Chen, Ningxin Jiao, Kui JiaICCV 2023 · 769 citations
- Extracting Triangular 3D Models, Materials, and Lighting From ImagesJacob Munkberg, Wenzheng Chen, Jon Hasselgren, Alex Evans et al.CVPR 2022 · 306 citations
Related papers
- Micro-Mesh ConstructionAndrea Maggiordomo, Henry Moreton, Marco TariniSIGGRAPH 2023 · 22 citations
- Differentiable Heightfield Path Tracing with Accelerated DiscontinuitiesXiaochun Tong, Hsueh-Ti Derek Liu, Yotam I. Gingold, Alec JacobsonSIGGRAPH 2023 · 4 citations
- Real-Time Hair Rendering with Hair MeshesGaurav Bhokare, Eisen Montalvo, Elie Diaz, Cem YukselSIGGRAPH 2024 · 14 citations
- DualPrim: Compact 3D Reconstruction with Positive and Negative PrimitivesXiaoxu Meng, Zhongmin Chen, Bo Yang, Weikai Chen et al.CVPR 2026
- Ray Tracing Structured AMR Data Using ExaBricksIngo Wald, Stefan Zellmann, Will Usher, Nate Morrical et al.IEEE VIS 2020 · 18 citations
