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

Haoxuan Li1, Ziya Erkoç1, Daniele Sirigatti2, Vladislav Rosov2, Lei Li3, Angela Dai1, Matthias Nießner1
1Technical University of Munich, 2AUDI AG, 3University of Virginia
Paper arXiv Code [TBA] Video
TriFlow teaser: NVF on a beetle (top-left) and a gallery of generated artist-like meshes (right).

TriFlow generates high-quality, artist-like mesh topology from input SDFs. Top Left: we introduce a Nearest-Vertex Vector Field (NVF) to transform discrete topology prediction into efficient, piecewise-continuous field modeling. Right: TriFlow robustly generalizes across diverse and complex geometries.

Results

Toggle each card to compare the input geometry against the TriFlow output (shaded + wireframe). Drag to orbit, scroll to zoom.

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 8× speedup.

Video

Method Overview

Method overview: NVF on the surface, latent flow-matching network, watershed clustering and constrained QEM extraction.

We introduce a novel generative approach to create compact, artist-like mesh topologies from signed distance field (SDF) inputs.

Our method consists of three major components:

  1. We define the NVF on the surface (local field directions color-coded) to represent the mesh topology;
  2. We train a latent flow-matching network to synthesize the NVF conditioned on the SDF input;
  3. We use the watershed algorithm to cluster the surface and a constrained QEM that only merges vertices in the same group to extract the artist-like mesh as output.

LOD Control

TriFlow can target different topology budgets while keeping the input geometry. Switch between Input and three levels of detail to see how connectivity adapts.

More Results

BibTeX

@inproceedings{li2026triflow,
  title = {TriFlow: Generating Artist-Like 3D Mesh Topology via Nearest-Vertex Vector Fields},
  author = {Li, Haoxuan and Erko{\c{c}}, Ziya and Sirigatti, Daniele and Rosov, Vladislav and Li, Lei and Dai, Angela and Nie{\ss}ner, Matthias},
  booktitle = {Proceedings of the European Conference on Computer Vision (ECCV)},
  year = {2026},
}