VertexRegen: Mesh Generation with Continuous Level of Detail
Xiang Zhang, Yawar Siddiqui, Armen Avetisyan, Chris Xie, Jakob J. Engel, Henry Howard-Jenkins
摘要
We introduce VertexRegen, a novel mesh generation framework that enables generation at a continuous level of detail. Existing autoregressive methods generate meshes in a partial-to-complete manner and thus intermediate steps of generation represent incomplete structures. VertexRegen takes inspiration from progressive meshes and reformulates the process as the reversal of edge collapse, i.e. vertex split, learned through a generative model. Experimental results demonstrate that VertexRegen produces meshes of comparable quality to state-of-the-art methods while uniquely offering anytime generation with the flexibility to halt at any step to yield valid meshes with varying levels of detail.
问问这篇 Paper
智能体会读完全文。
Lune 把这篇 Paper 索引到了每一个公式,引用它的顶会 Paper 也一样。你提问,回答直接引用原文。
引用它的顶会 Paper7
- QuadGPT: Native Quadrilateral Mesh Generation with Autoregressive ModelsJian Liu, Chunshi Wang, Song Guo, Haohan Weng 等ICLR 2026 · 被引用 15 次
- LoST: Level of Semantics Tokenization for 3D ShapesNiladri Shekhar Dutt, Zifan Shi, Paul Guerrero, Chun-Hao Paul Huang 等CVPR 2026 · 被引用 4 次
- ExMesh: EXplicit Mesh Reconstruction with Topology AdaptationChuanjin Fan, Lifan Wu, Wenjie Chang, Hanzhi Chang 等CVPR 2026 · 被引用 2 次
- FlashMesh: Faster and Better Autoregressive Mesh Synthesis via Structured SpeculationTingrui Shen, Yiheng Zhang, Chen Tang, Chuan Ping 等CVPR 2026 · 被引用 2 次
- PixARMesh: Autoregressive Mesh-Native Single-View Scene ReconstructionXiang Zhang, Sohyun Yoo, Hongrui Wu, Chuan Li 等CVPR 2026 · 被引用 2 次
它引用的顶会 Paper29
- Visual Instruction TuningHaotian Liu, Chunyuan Li, Qingyang Wu, Yong Jae LeeNeurIPS 2023 · 被引用 11,349 次
- DreamGaussian: Generative Gaussian Splatting for Efficient 3D Content CreationJiaxiang Tang, Jiawei Ren, Hang Zhou, Ziwei Liu 等ICLR 2024 · 被引用 955 次
- LRM: Large Reconstruction Model for Single Image to 3DYicong Hong, Kai Zhang, Jiuxiang Gu, Sai Bi 等ICLR 2024 · 被引用 813 次
- LION: Latent Point Diffusion Models for 3D Shape GenerationXiaohui Zeng, Arash Vahdat, Francis Williams, Zan Gojcic 等NeurIPS 2022 · 被引用 752 次
- 3D Shape Generation and Completion through Point-Voxel DiffusionLinqi Zhou, Yilun Du, Jiajun WuICCV 2021 · 被引用 681 次
相关 Paper
- ARMesh: Autoregressive Mesh Generation via Next-Level-of-Detail PredictionJiabao Lei, Kewei Shi, Zhihao Liang, Kui JiaNeurIPS 2025 · 被引用 12 次
- MeshFlow: Efficient Artistic Mesh Generation via MeshVAE and Flow-based Diffusion TransformerWeiyu Li, Antoine Toisoul, Tom Monnier, Roman Shapovalov 等CVPR 2026 · 被引用 7 次
- TreeMeshGPT: Artistic Mesh Generation with Autoregressive Tree SequencingStefan Lionar, Jiabin Liang, Gim Hee LeeCVPR 2025
- MeshRipple: Structured Autoregressive Generation of Artist-MeshesJunKai Lin, Hang Long, Huipeng Guo, Jielei Zhang 等CVPR 2026 · 被引用 9 次
- PartDiffuser: Part-wise 3D Mesh Generation via Discrete DiffusionYichen Yang, Hong Li, Haodong Zhu, Linin Yang 等CVPR 2026 · 被引用 4 次
