The reviewed record of science sign in
Pith

arxiv: 2312.11417 · v1 · pith:PF4W3ESV · submitted 2023-12-18 · cs.CV

PolyDiff: Generating 3D Polygonal Meshes with Diffusion Models

Reviewed by Pithpith:PF4W3ESVopen to challenge →

classification cs.CV
keywords meshesdiffusionpolygonaldenoisingpolydiffapproachcapablegenerating
0
0 comments X
read the original abstract

We introduce PolyDiff, the first diffusion-based approach capable of directly generating realistic and diverse 3D polygonal meshes. In contrast to methods that use alternate 3D shape representations (e.g. implicit representations), our approach is a discrete denoising diffusion probabilistic model that operates natively on the polygonal mesh data structure. This enables learning of both the geometric properties of vertices and the topological characteristics of faces. Specifically, we treat meshes as quantized triangle soups, progressively corrupted with categorical noise in the forward diffusion phase. In the reverse diffusion phase, a transformer-based denoising network is trained to revert the noising process, restoring the original mesh structure. At inference, new meshes can be generated by applying this denoising network iteratively, starting with a completely noisy triangle soup. Consequently, our model is capable of producing high-quality 3D polygonal meshes, ready for integration into downstream 3D workflows. Our extensive experimental analysis shows that PolyDiff achieves a significant advantage (avg. FID and JSD improvement of 18.2 and 5.8 respectively) over current state-of-the-art methods.

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 8 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. MeshFlow: Mesh Generation with Equivariant Flow Matching

    cs.GR 2026-06 unverdicted novelty 7.0

    MeshFlow applies equivariant optimal-transport flow matching to generate triangle meshes as soups, matching autoregressive quality with an 18x inference speedup.

  2. Mesh BDF: Barycentric Dominance Field for 3D Native Mesh Generation

    cs.CV 2026-06 unverdicted novelty 6.0

    Barycentric Dominance Field converts discrete mesh connectivity into a continuous surface signal that diffusion models can use directly for higher-quality native 3D mesh generation.

  3. VideoMDM: Towards 3D Human Motion Generation From 2D Supervision

    cs.LG 2026-06 unverdicted novelty 6.0

    VideoMDM learns coherent 3D motion manifolds from 2D supervision alone by using a pretrained lifter as noisy teacher, depth-weighted 2D reprojection loss, and adapted regularizers, nearly matching fully 3D-supervised ...

  4. DB-3DME: From Dataset to Benchmark for Human-aligned Automatic 3D Mesh Evaluation

    cs.CV 2026-06 unverdicted novelty 6.0

    DB-3DME supplies a human-rated 3D mesh dataset and shows that fine-tuning the visual encoder of Qwen-2.5-VL-7B produces automatic evaluations that align better with humans than prior VLMs.

  5. Art3D: Training-Free 3D Generation from Flat-Colored Illustration

    cs.CV 2025-04 unverdicted novelty 6.0

    Art3D enhances flat-colored 2D illustrations with 3D illusion using pre-trained 2D model features and VLM realism evaluation, then generates 3D, while introducing the Flat-2D benchmark dataset.

  6. InstantMesh: Efficient 3D Mesh Generation from a Single Image with Sparse-view Large Reconstruction Models

    cs.CV 2024-04 unverdicted novelty 6.0

    InstantMesh produces diverse, high-quality 3D meshes from single images in seconds by combining a multi-view diffusion model with a sparse-view large reconstruction model and optimizing directly on meshes.

  7. From Visual Synthesis to Interactive Worlds: Toward Production-Ready 3D Asset Generation

    cs.GR 2026-04 unverdicted novelty 5.0

    The paper surveys 3D asset generation methods and organizes them around the full production pipeline to assess which outputs meet engine-level requirements for interactive applications.

  8. From Visual Synthesis to Interactive Worlds: Toward Production-Ready 3D Asset Generation

    cs.GR 2026-04 unverdicted novelty 4.0

    The paper surveys 3D content generation literature using a taxonomy of asset types and production stages to evaluate progress toward engine-ready assets.