arXiv Computer Vision October 7, 2026 By Junkai Lin, Tianhao Zhao, Hang Long, Huipeng Guo, Jielei Zhang, Youjia Zhang, Jiale Xu, Wenbing Li, Rendong Liang, Jozef Hladk\'y, Matthias Nie{\ss}ner, Yuanming Hu, Wei Yang

MeshOctave: Vertex Split-and-Rewire Cascades for Native Mesh Generation

Read the original on arXiv Computer Vision →

MeshOctave introduces a novel approach to native mesh generation that replaces sequential autoregressive or heuristic flow models with a parallel, coarse-to-fine paradigm. By defining scales through dyadic spatial grid resolutions, it collapses vertices deterministically and then performs split-and-rewire operations to reconstruct fine topology without serialization. The method employs a scale-conditioned masked-uniform discrete diffusion model, achieving higher geometric fidelity and topological validity while supporting adaptive resolution refinement and mesh subdivision tasks.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Computer Vision.

diffusion

arXiv Computer Vision

Oct 1

MeshOctave generates meshes via cascading resolution transitions

arXiv:2609.38985v1 Announce Type: new Abstract: Generating compact, artist-style meshes with explicit topology typically relies on autoregressive models which incur prohibitive sequential per-token c...

By Junkai Lin, Tianhao Zhao, Hang Long, Huipeng Guo, Jielei Zhang, Youjia Zhang, Jiale Xu, Wenbing Li, Rendong Liang, Jozef Hladk\'y, Matthias Nie{\ss}ner, Yuanming Hu, Wei Yang

diffusion

Hugging Face Trending Papers

Jun 25

SubdivAR: Autoregressive Next-Scale Prediction for Neural Mesh Subdivision

Mesh subdivision is a fundamental operation for converting coarse, editable meshes into high-resolution surfaces, with broad applications in digital asset creation. Classical rule-based schemes rely on fixed local refinement rules and often produce over-smoothed surfaces.

llms benchmarks

arXiv Computer Vision

4d ago

MeshCarve: Artisan Mesh Generation with Flow Matching in Compact Latent Spaces

MeshCarve introduces a flow‑matching approach that generates artisan meshes entirely within compact latent spaces, separating vertex positions and edge connections to avoid joint encoding issues. It employs a hierarchical sparse transformer backbone with VertexVAE and EdgeVAE, which anchor on discrete vertices to drastically shorten token sequences and use spatial‑aware compression without sacrificing reconstruction quality. The method outperforms state‑of‑the‑art autoregressive and flow‑matching techniques on Objaverse and generalizes to Toys4K, representing one of the first fully compressed latent artisan mesh generators.

By Xiyu Wang, Ruocheng Wu, Yufei Wang, Zhihao Li, Lanqing Guo, Bihan Wen

llms rag diffusion benchmarks

Hugging Face Trending Papers

Jul 15

Nexus: Native Mesh Generation with Diffusion

Generating high-quality triangle meshes is essential for film, gaming, and interactive 3D applications. Mainstream methods rely on mesh serialization and autoregressive processes, which stuggles in effective inference and is sensitive to error accumulation.

rag diffusion benchmarks

arXiv AI

Aug 11

P2Voxel: Pyramid Pivot Voxelization for 3D Mesh Tokenization

arXiv:2608. 07549v1 Announce Type: cross Abstract: Triangle meshes provide explicit and accurate surface geometry, yet their irregular topology connectivity makes 3D mesh tokenization a geometric sampling problem: how to sample and organize geometric evidence into compact, structured and learnable tokens.

By Zhenhong Sun, Haozhe Liu, Yifu Wang, Xibin Song, Senbo Wang, Huadong Mo, Daoyi Dong, Hongdong Li, Pan Ji

nlp

arXiv AI

Oct 2

SILSA: Sliding-Window Slice Latents for Topology-Preserving High-Resolution 3D Generation

arXiv:2610.02201v1 Announce Type: cross Abstract: High-resolution 3D generation increasingly relies on voxel latents and multi-stage pipelines that first predict active structure and then synthesize...

By Tianjiao Yu, Xinzhuo Li, Yifan Shen, Ying Shen, Kiet A. Nguyen, Adheesh Sunil Juvekar, Ismini Lourentzou