PolyFlow: Continuous Topology Embedding Flow Matching for Artist-style Mesh Generation
Open Access
- 30 November 2026
- conference paper
- Published by Association for Computing Machinery (ACM)
- p. 1-10
Abstract
No abstract availableFunding Information
- National Natural Science Foundation of China (62293554)
- National Natural Science Foundation of China (U2336212)
- National Science and Technology Major Project (2023ZD0121300)
- "Pioneer" and "Leading Goose" R&D Program of Zhejiang (2025C02022)
- "Pioneer" and "Leading Goose" R&D Program of Zhejiang (2024C01161)
- Zhejiang Provincial Natural Science Foundation of China (LZ24F020002)
- Ningbo Innovation "Yongjiang 2035" Key Research and Development Programme (2024Z292)
- Young Elite Scientists Sponsorship Program by CAST (2023QNRC001)
This publication has 16 references indexed in Scilit:
- DeepMesh: Auto-Regressive Artist-Mesh Creation with Reinforcement Learning2025
- Scaling Mesh Generation via Compressive Tokenization2025
- SiT: Exploring Flow and Diffusion-Based Generative Models with Scalable Interpolant Transformers2024
- MeshGPT: Generating Triangle Meshes with Decoder-Only Transformers2024
- Scalable Diffusion Models with Transformers2023
- Objaverse: A Universe of Annotated 3D Objects2023
- 3D-FUTURE: 3D Furniture Shape with TextUREInternational Journal of Computer Vision, 2021
- Using Shape to Categorize: Low-Shot Learning with an Explicit Shape Bias2021
- PointTriNet: Learned Triangulation of 3D Point Sets2020
- DeepSDF: Learning Continuous Signed Distance Functions for Shape Representation2019