mlsanityData to 7 Oct 2026

DMesh: A Differentiable Mesh Representation

arXiv 2404.13445 ↗First posted 20 Apr 2024cs.CV cs.GRcited by 9

Not on the map. Why?

Abstract (arXiv)

We present a differentiable representation, DMesh, for general 3D triangular meshes. DMesh considers both the geometry and connectivity information of a mesh. In our design, we first get a set of convex tetrahedra that compactly tessellates the domain based on Weighted Delaunay Triangulation (WDT), and select triangular faces on the tetrahedra to define the final mesh. We formulate probability of faces to exist on the actual surface in a differentiable manner based on the WDT. This enables DMesh to represent meshes of various topology in a differentiable way, and allows us to reconstruct the mesh under various observations, such as point cloud and multi-view images using gradient-based optimization. The source code and full paper is available at: https://sonsang.github.io/dmesh-project.

Key facts. Cited by 9 papers in the map (data through 7 Oct 2026). Builds on 25 of its 49 references that are in the map. First posted on arXiv 20 Apr 2024.

Builds on

25 of 49 references.

References · 25

  1. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  2. 20233D Gaussian Splatting for Real-Time Radiance Field Renderingcited by 6,141
  3. 2021NeuS: Learning Neural Implicit Surfaces by Volume Rendering for Multi-view Reconstructioncited by 1,701
  4. 2022TensoRF: Tensorial Radiance Fieldscited by 1,275
  5. 2021Volume Rendering of Neural Implicit Surfacescited by 990
  6. 2020Neural Sparse Voxel Fieldscited by 959
  7. 2020NeRF++: Analyzing and Improving Neural Radiance Fieldscited by 857
  8. 2021UNISURF: Unifying Neural Implicit Surfaces and Radiance Fields for Multi-View Reconstructioncited by 643
  9. 2021Deep Marching Tetrahedra: a Hybrid Representation for High-Resolution 3D Shape Synthesiscited by 459
  10. 2020Modular Primitives for High-Performance Differentiable Renderingcited by 439
  11. 2019Soft Rasterizer: A Differentiable Renderer for Image-based 3D Reasoningcited by 420
  12. 2021Extracting Triangular 3D Models, Materials, and Lighting From Imagescited by 363
13 more
  1. 2022NeuS2: Fast Learning of Neural Implicit Surfaces for Multi-view Reconstructioncited by 311
  2. 2019Learning to Predict 3D Objects with an Interpolation-based Differentiable Renderercited by 221
  3. 2019BSP-Net: Generating Compact Meshes via Binary Space Partitioningcited by 205
  4. 2023Flexible Isosurface Extraction for Gradient-Based Mesh Optimizationcited by 138
  5. 2022Neural Dual Contouringcited by 71
  6. 2022NeuralUDF: Learning Unsigned Distance Fields for Multi-view Reconstruction of Surfaces with Arbitrary Topologiescited by 62
  7. 2020Fully Convolutional Mesh Autoencoder using Efficient Spatially Varying Kernelscited by 53
  8. 2022A Level Set Theory for Neural Implicit Evolution under Explicit Flowscited by 42
  9. 2023NeUDF: Leaning Neural Unsigned Distance Fields with Volume Renderingcited by 40
  10. 2023NeuManifold: Neural Watertight Manifold Reconstruction with Efficient and High-Quality Rendering Supportcited by 25
  11. 2023Ghost on the Shell: An Expressive Representation of General 3D Shapescited by 24
  12. 2021DeepMesh: Differentiable Iso-Surface Extractioncited by 14
  13. 2021Differentiable Surface Triangulationcited by 14

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 3; 2026: 6.

9 papers.

  1. 2025SparseFlex: High-Resolution and Arbitrary-Topology 3D Shape Modelingcited by 76
  2. 2025ARMesh: Autoregressive Mesh Generation via Next-Level-of-Detail Predictioncited by 11
  3. 2026LATO.2: Factorized 3D Mesh Generation with Vertex and Topology Flowcited by 6
  4. 2025Triangle Splatting+: Differentiable Rendering with Opaque Trianglescited by 5
  5. 2026From Blobs to Spokes: High-Fidelity Surface Reconstruction via Oriented Gaussianscited by 2
  6. 2026ExMesh: Explicit Mesh Reconstruction with Topology Adaptationcited by 2
  7. 2026PolyFlow: Continuous Topology Embedding Flow Matching for Artist-style Mesh Generationcited by 1
  8. 2026DiffTrans: Differentiable Geometry-Materials Decomposition for Reconstructing Transparent Objectscited by 0
  9. 2026DiffGI: Differentiable Geometry Images for High-Fidelity Thin-Shell 3D Generationcited by 0