InterCoser: Interactive 3D Character Creation with Disentangled Fine-Grained Features
Yi Wang, Jian Ma, Zhuo Su, Guidong Wang, Jingyu Yang, Yu-Kun Lai, Kun Li
摘要
This paper aims to interactively generate and edit disentangled 3D characters based on precise user instructions. Existing methods generate and edit 3D characters via rough and simple editing guidance and entangled representations, making it difficult to achieve precise and comprehensive control over fine-grained local editing and free clothing transfer for characters. To enable accurate and intuitive control over the generation and editing of high-quality 3D characters with freely interchangeable clothing, we propose a novel user-interactive approach for disentangled 3D character creation. Specifically, to achieve precise control over 3D character generation and editing, we introduce two user-friendly interaction approaches: a sketch-based layered character generation/editing method, which supports clothing transfer; and a 3D-proxy-based part-level editing method, enabling fine-grained disentangled editing. To enhance 3D character quality, we propose a 3D Gaussian reconstruction strategy guided by geometric priors, ensuring that 3D characters exhibit detailed local geometry and smooth global surfaces. Extensive experiments on both public datasets and in-the-wild data demonstrate that our approach not only generates high-quality disentangled 3D characters but also supports precise and fine-grained editing through user interaction.
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。
它引用的顶会 Paper28
- 3D Gaussian Splatting for Real-Time Radiance Field RenderingBernhard Kerbl, Georgios Kopanas, Thomas Leimkühler, George DrettakisSIGGRAPH 2023 · 被引用 5,687 次
- Pick-a-Pic: An Open Dataset of User Preferences for Text-to-Image GenerationYuval Kirstain, Adam Polyak, Uriel Singer, Shahbuland Matiana 等NeurIPS 2023 · 被引用 1,192 次
- LightGlue: Local Feature Matching at Light SpeedPhilipp Lindenberger, Paul-Edouard Sarlin, Marc PollefeysICCV 2023 · 被引用 936 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
- Triplane Meets Gaussian Splatting: Fast and Generalizable Single-View 3D Reconstruction with TransformersZi-Xin Zou, Zhipeng Yu, Yuan-Chen Guo, Yangguang Li 等CVPR 2024 · 被引用 119 次
相关 Paper
- AttriHuman-3D: Editable 3D Human Avatar Generation with Attribute Decomposition and IndexingFan Yang, Tianyi Chen, Xiaosheng He, Zhongang Cai 等CVPR 2024 · 被引用 6 次
- LayGA: Layered Gaussian Avatars for Animatable Clothing TransferSiyou Lin, Zhe Li, Zhaoqi Su, Zerong Zheng 等SIGGRAPH 2024 · 被引用 27 次
- DRiVE: Diffusion-based Rigging Empowers Generation of Versatile and Expressive CharactersMingze Sun, Junhao Chen, Junting Dong, Yurun Chen 等CVPR 2025
- SemanticGarment: Semantic-Controlled Generation and Editing of 3D Gaussian GarmentsRuiyan Wang, Zhengxue Cheng, Zonghao Lin, Jun Ling 等ACM MM 2025
- DeepFaceEditing: deep face generation and editing with disentangled geometry and appearance controlShu-Yu Chen, Feng-Lin Liu, Yu-Kun Lai, Paul L. Rosin 等SIGGRAPH 2021 · 被引用 35 次
