DMesh++: An Efficient Differentiable Mesh for Complex Shapes
Sanghyun Son, Matheus Gadelha, Yang Zhou, Matthew Fisher, Zexiang Xu, Yi-Ling Qiao, Ming C. Lin, Yi Zhou
Abstract
Point Cloud Recon. (b) 3D Point Cloud Recon. (b) 3D Multi View Recon.
Figure 1. DMesh++ for complex 2D and 3D shapes. DMesh++ encodes all geometric and topological information into continuous point features. (a) By optimizing these point features, DMesh++ is able to reconstruct complex 2D drawings from sample points. (b) This approach is also applicable to 3D, where it reconstructs the complex geometric structure of DNA from a point cloud. (c) By incorporating additional color features, DMesh++ can reconstruct complex, colored 3D shapes from multi-view images. For each result, the "imaginary" part is rendered in gray, while the "real" part-which defines the final mesh-is rendered in other colors. (Sec. 3.1).
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 893b5ebf-0877-41f7-8848-059b9df557daCited by top-tier papers2
- MeshFlow: Efficient Artistic Mesh Generation via MeshVAE and Flow-based Diffusion TransformerWeiyu Li, Antoine Toisoul, Tom Monnier, Roman Shapovalov et al.CVPR 2026 · 7 citations
- ExMesh: EXplicit Mesh Reconstruction with Topology AdaptationChuanjin Fan, Lifan Wu, Wenjie Chang, Hanzhi Chang et al.CVPR 2026 · 2 citations
Builds on22
- 3D Gaussian Splatting for Real-Time Radiance Field RenderingBernhard Kerbl, Georgios Kopanas, Thomas Leimkühler, George DrettakisSIGGRAPH 2023 · 5,687 citations
- NeuS: Learning Neural Implicit Surfaces by Volume Rendering for Multi-view ReconstructionPeng Wang, Lingjie Liu, Yuan Liu, Christian Theobalt et al.NeurIPS 2021 · 2,500 citations
- Volume Rendering of Neural Implicit SurfacesLior Yariv, Jiatao Gu, Yoni Kasten, Yaron LipmanNeurIPS 2021 · 1,421 citations
- UNISURF: Unifying Neural Implicit Surfaces and Radiance Fields for Multi-View ReconstructionMichael Oechsle, Songyou Peng, Andreas GeigerICCV 2021 · 885 citations
- Soft Rasterizer: A Differentiable Renderer for Image-Based 3D ReasoningShichen Liu, Weikai Chen, Tianye Li, Hao LiICCV 2019 · 789 citations
Related papers
- DMesh: A Differentiable Mesh RepresentationSanghyun Son, Matheus Gadelha, Yang Zhou, Zexiang Xu et al.NeurIPS 2024 · 11 citations
- Point2CAD: Reverse Engineering CAD Models from 3D Point CloudsYujia Liu, Anton Obukhov, Jan Dirk Wegner, Konrad SchindlerCVPR 2024
- Point2Mesh: a self-prior for deformable meshesRana Hanocka, Gal Metzer, Raja Giryes, Daniel Cohen-OrSIGGRAPH 2020 · 243 citations
- DC-GNet: Deep Mesh Relation Capturing Graph Convolution Network for 3D Human Shape ReconstructionShihao Zhou, Mengxi Jiang, Shanshan Cai, Yunqi LeiACM MM 2021 · 14 citations
- Neural Template: Topology-aware Reconstruction and Disentangled Generation of 3D MeshesKa-Hei Hui, Ruihui Li, Jingyu Hu, Chi-Wing FuCVPR 2022 · 24 citations
