Pith. sign in

REVIEW 7 cited by

MeshGPT: Generating Triangle Meshes with Decoder-Only Transformers

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2311.15475 v1 pith:L77WN5NA submitted 2023-11-27 cs.CV cs.LG

classification cs.CVcs.LG
keywords meshestriangleembeddingsgeneratingmeshmeshgptapproachautoregressively
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

We introduce MeshGPT, a new approach for generating triangle meshes that reflects the compactness typical of artist-created meshes, in contrast to dense triangle meshes extracted by iso-surfacing methods from neural fields. Inspired by recent advances in powerful large language models, we adopt a sequence-based approach to autoregressively generate triangle meshes as sequences of triangles. We first learn a vocabulary of latent quantized embeddings, using graph convolutions, which inform these embeddings of the local mesh geometry and topology. These embeddings are sequenced and decoded into triangles by a decoder, ensuring that they can effectively reconstruct the mesh. A transformer is then trained on this learned vocabulary to predict the index of the next embedding given previous embeddings. Once trained, our model can be autoregressively sampled to generate new triangle meshes, directly generating compact meshes with sharp edges, more closely imitating the efficient triangulation patterns of human-crafted meshes. MeshGPT demonstrates a notable improvement over state of the art mesh generation methods, with a 9% increase in shape coverage and a 30-point enhancement in FID scores across various categories.

Discussion (0). Sign in to comment.

Forward citations

Cited by 7 Pith papers

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

  1. Mat\'ern Noise for Triangulation-Agnostic Flow Matching on Meshes

    cs.GR 2026-05 unverdicted novelty 7.0 of 10

    Proposes discretized Matérn process noise for triangulation-agnostic flow matching on meshes with PoissonNet denoiser, tested on elastic states and humanoid poses for meshes exceeding one million triangles.

  2. MeshFlow: Efficient Artistic Mesh Generation via MeshVAE and Flow-based Diffusion Transformer

    cs.CV 2026-06 unverdicted novelty 6.0 of 10

    MeshFlow uses a contrastive MeshVAE for compact mesh latents and a flow transformer for parallel generation, claiming 18x speedup over autoregressive methods with high accuracy on standard metrics.

  3. Bounding Global and Local Compression Error of Signal Parameterizations

    eess.IV 2026-05 unverdicted novelty 6.0 of 10

    A non-asymptotic bound on compression error for signal parameterizations derived from differences in predictions at varying compression levels, verified empirically across fitting and inverse problems.

  4. GaussianGPT: Towards Autoregressive 3D Gaussian Scene Generation

    cs.CV 2026-03 conditional novelty 6.0 of 10

    A causal transformer with 3D RoPE generates vector-quantized 3D Gaussian latent grids autoregressively, enabling unconditional synthesis, completion, and open-ended outpainting of indoor scenes.

  5. Unifi3D: A Study on 3D Representations for Generation and Reconstruction in a Common Framework

    cs.GR 2025-09 conditional novelty 6.0 of 10

    SDF grids reconstruct best, Dual Octrees score best on automatic generation metrics, but users prefer SDF output, and reconstruction plus compression errors make up a large share of generation error.

  6. CNS-Edit++: Category-Agnostic 3D Editing with Coupled Neural Shape Representation

    cs.CV 2026-07 conditional novelty 5.0 of 10

    Coupling a global latent code with a 3D feature volume lets off-the-shelf 3D generators perform local semantic edits — copy, delete, resize, mix, and drag — across object categories while preserving unedited regions.

  7. CG-MLLM: Captioning and Generating 3D content via Multi-modal Large Language Models

    cs.CV 2026-01 unverdicted novelty 5.0 of 10

    CG-MLLM is a multimodal LLM using a Mixture-of-Transformer architecture with separate TokenAR and BlockAR components integrated with a pre-trained vision-language backbone and 3D VAE to enable 3D captioning and high-f...

Pith tools