TriFlow: Generating Artist-Like 3D Mesh Topology via Nearest-Vertex Vector Fields

• URL: http://arxiv.org/abs/2606.20131v2
• Date: Fri, 19 Jun 2026 20:50:59 GMT
• Title: TriFlow: Generating Artist-Like 3D Mesh Topology via Nearest-Vertex Vector Fields
• Abstract summary: TriFlow is a new generative approach for producing compact 3D meshes with artist-like triangle topology directly from input geometry conditions such as signed distance fields.<n>Experiments demonstrate that TriFlow achieves stronger generalization and significantly improved topology quality compared to state-of-the-art learning-based approaches.
• Score: 72.76537377865192
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: We present TriFlow, a new generative approach for producing compact 3D meshes with artist-like triangle topology directly from input geometry conditions such as signed distance fields. Our key insight is to represent mesh topology as a nearest-vertex vector field (NVF) defined over the surface, where each point encodes its association to the nearest triangle vertex in the local barycentric frame. We train a latent flow-matching model to synthesize this field, enabling topology generation conditioned on the input geometry. To extract a coherent mesh, we cluster surface regions using the generated NVF and guide a constrained quadric error metric (QEM) mesh simplification with topology-aware optimization. This yields output meshes that closely match the input geometry while exhibiting structured, artist-like connectivity. Experiments demonstrate that TriFlow achieves stronger generalization and significantly improved topology quality compared to state-of-the-art learning-based approaches, alongside 90% lower Chamfer Distance and an 8x speedup.

Related papers

• HoloTetSphere: Unified TetSphere Mesh Reconstruction for Physical Simulations [16.69225871436957]
  We propose a topology-adaptive framework for holistic tetrahedral mesh reconstruction through end-to-end topological and geometric optimization.<n>Our method outperforms state-of-the-art techniques by achieving superior geometric accuracy and producing coherent, single-connected tetrahedral meshes.
  arXiv  Detail & Related papers  (2026-07-09T12:21:43Z)
• LATO: 3D Mesh Flow Matching with Structured TOpology Preserving LAtents [43.84310366771089]
  LATO is a novel topology-preserving latent representation that enables scalable, flow matching-based synthesis of explicit 3D meshes.<n>For generative modeling, LATO adopts a two-stage flow matching process, first synthesizing the structure voxels and subsequently refining the voxel-wise topology features.<n>Compared to prior isosurface/triangle-based diffusion models and autoregressive generation approaches, LATO generates meshes with complex geometry, well-formed topology while being highly efficient in inference.
  arXiv  Detail & Related papers  (2026-03-06T15:09:25Z)
• Hierarchical Neural Surfaces for 3D Mesh Compression [0.0]
  Implicit Neural Representations (INRs) have been demonstrated to achieve state-of-the-art compression of a broad range of modalities such as images, videos, 3D surfaces, and audio.<n>Most studies have focused on building neural counterparts of traditional implicit representations of 3D geometries, such as signed distance functions.
  arXiv  Detail & Related papers  (2025-12-17T21:32:04Z)
• SpaceMesh: A Continuous Representation for Learning Manifold Surface Meshes [61.110517195874074]
  We present a scheme to directly generate manifold, polygonal meshes of complex connectivity as the output of a neural network.<n>Our key innovation is to define a continuous latent connectivity space at each mesh, which implies the discrete mesh.<n>In applications, this approach not only yields high-quality outputs from generative models, but also enables directly learning challenging geometry processing tasks such as mesh repair.
  arXiv  Detail & Related papers  (2024-09-30T17:59:03Z)
• MeshGPT: Generating Triangle Meshes with Decoder-Only Transformers [32.169007676811404]
  MeshGPT is a new approach for generating triangle meshes that reflects the compactness typical of artist-created meshes. Inspired by recent advances in powerful large language models, we adopt a sequence-based approach to autoregressively generate triangle meshes as triangles.
  arXiv  Detail & Related papers  (2023-11-27T01:20:11Z)
• GeoUDF: Surface Reconstruction from 3D Point Clouds via Geometry-guided Distance Representation [73.77505964222632]
  We present a learning-based method, namely GeoUDF, to tackle the problem of reconstructing a discrete surface from a sparse point cloud. To be specific, we propose a geometry-guided learning method for UDF and its gradient estimation. To extract triangle meshes from the predicted UDF, we propose a customized edge-based marching cube module.
  arXiv  Detail & Related papers  (2022-11-30T06:02:01Z)
• Deep Marching Tetrahedra: a Hybrid Representation for High-Resolution 3D Shape Synthesis [90.26556260531707]
  DMTet is a conditional generative model that can synthesize high-resolution 3D shapes using simple user guides such as coarse voxels. Unlike deep 3D generative models that directly generate explicit representations such as meshes, our model can synthesize shapes with arbitrary topology.
  arXiv  Detail & Related papers  (2021-11-08T05:29:35Z)
• Differentiable Surface Triangulation [40.13834693745158]
  We present a differentiable surface triangulation that enables optimization for any per-vertex or per-face differentiable objective function over the space of underlying surface triangulations. Our method builds on the result that any 2D triangulation can be achieved by a suitably weighted Delaunay triangulation. We extend the algorithm to 3D by decomposing shapes into developable sets and differentiably meshing each set with suitable boundary constraints.
  arXiv  Detail & Related papers  (2021-09-22T12:42:43Z)
• PU-Flow: a Point Cloud Upsampling Networkwith Normalizing Flows [58.96306192736593]
  We present PU-Flow, which incorporates normalizing flows and feature techniques to produce dense points uniformly distributed on the underlying surface. Specifically, we formulate the upsampling process as point in a latent space, where the weights are adaptively learned from local geometric context. We show that our method outperforms state-of-the-art deep learning-based approaches in terms of reconstruction quality, proximity-to-surface accuracy, and computation efficiency.
  arXiv  Detail & Related papers  (2021-07-13T07:45:48Z)
• Primal-Dual Mesh Convolutional Neural Networks [62.165239866312334]
  We propose a primal-dual framework drawn from the graph-neural-network literature to triangle meshes. Our method takes features for both edges and faces of a 3D mesh as input and dynamically aggregates them. We provide theoretical insights of our approach using tools from the mesh-simplification literature.
  arXiv  Detail & Related papers  (2020-10-23T14:49:02Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.