paper-with-me

Papers

MeshRipple: Structured Autoregressive Generation of Artist-Meshes

2025-12-08 · Junkai Lin, Hang Long, Huipeng Guo, Jielei Zhang, JiaYi Yang, Tianle Guo, Yang Yang, Jianwen Li, Wenxiao Zhang, Matthias Nießner, Wei Yang arxiv

Meshes serve as a primary representation for 3D assets. Autoregressive mesh generators serialize faces into sequences and train on truncated segments with sliding-window inference to cope with memory limits. However, this mismatch breaks long-range geometric dependencies, producing holes and fragmented components. To address this critical limitation, we introduce MeshRipple, which expands a mesh outward from an active generation frontier, akin to a ripple on a surface. MeshRipple rests on three key innovations: a frontier-aware BFS tokenization that aligns the generation order with surface topology; an expansive prediction strategy that maintains coherent, connected surface growth; and a sparse-attention global memory that provides an effectively unbounded receptive field to resolve long-range topological dependencies. This integrated design enables MeshRipple to generate meshes with high surface fidelity and topological completeness, outperforming strong recent baselines.

📄 PDF Abstract BibTeX arXiv:2512.07514

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

MeshMosaic: Scaling Artist Mesh Generation via Local-to-Global Assembly

2025-09-24 · Rui Xu, Tianyang Xue, Qiujie Dong, Le Wan 외 arxiv

Scaling artist-designed meshes to high triangle numbers remains challenging for autoregressive generative models. Existing transformer-based methods suffer from long-sequence bottlenecks and limited quantization resoluti…

MeshAnything V2: Artist-Created Mesh Generation With Adjacent Mesh Tokenization

2024-08-05 · YiWen Chen, Yikai Wang, Yihao Luo, Zhengyi Wang 외

Meshes are the de facto 3D representation in the industry but are labor-intensive to produce. Recently, a line of research has focused on autoregressively generating meshes. This approach processes meshes into a sequence…

TreeMeshGPT: Artistic Mesh Generation with Autoregressive Tree Sequencing

2025-03-14 · CVPR 2025 1 · Stefan Lionar, Jiabin Liang, Gim Hee Lee

We introduce TreeMeshGPT, an autoregressive Transformer designed to generate high-quality artistic meshes aligned with input point clouds. Instead of the conventional next-token prediction in autoregressive Transformer, …

MeshAnything: Artist-Created Mesh Generation with Autoregressive Transformers

2024-06-14 · YiWen Chen, Tong He, Di Huang, Weicai Ye 외

Recently, 3D assets created via reconstruction and generation have matched the quality of manually crafted assets, highlighting their potential for replacement. However, this potential is largely unrealized because these…

Decoder

FastMesh: Efficient Artistic Mesh Generation via Component Decoupling

2025-08-26 · Jeonghwan Kim, Yushi Lan, Armando Fortes, Yongwei Chen 외 arxiv

Recent mesh generation approaches typically tokenize triangle meshes into sequences of tokens and train autoregressive models to generate these tokens sequentially. Despite substantial progress, such token sequences inev…