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
Abstract
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.
Ask about this paper
Your agent reads all of it.
Lune indexed this paper to the last equation, along with the top-tier papers that cite it. Ask a question and the answer quotes them.
Your agent calls
Luneget_paper_fulltext
Free to start. No credit card required.
Terminal
Install the CLIlune papers fulltext 2f693d5b-a757-4ae3-bcc9-20a7d5407a80Builds on28
- 3D Gaussian Splatting for Real-Time Radiance Field RenderingBernhard Kerbl, Georgios Kopanas, Thomas Leimkühler, George DrettakisSIGGRAPH 2023 · 5,687 citations
- Pick-a-Pic: An Open Dataset of User Preferences for Text-to-Image GenerationYuval Kirstain, Adam Polyak, Uriel Singer, Shahbuland Matiana et al.NeurIPS 2023 · 1,192 citations
- LightGlue: Local Feature Matching at Light SpeedPhilipp Lindenberger, Paul-Edouard Sarlin, Marc PollefeysICCV 2023 · 936 citations
- LRM: Large Reconstruction Model for Single Image to 3DYicong Hong, Kai Zhang, Jiuxiang Gu, Sai Bi et al.ICLR 2024 · 813 citations
- Triplane Meets Gaussian Splatting: Fast and Generalizable Single-View 3D Reconstruction with TransformersZi-Xin Zou, Zhipeng Yu, Yuan-Chen Guo, Yangguang Li et al.CVPR 2024 · 119 citations
Related papers
- AttriHuman-3D: Editable 3D Human Avatar Generation with Attribute Decomposition and IndexingFan Yang, Tianyi Chen, Xiaosheng He, Zhongang Cai et al.CVPR 2024 · 6 citations
- LayGA: Layered Gaussian Avatars for Animatable Clothing TransferSiyou Lin, Zhe Li, Zhaoqi Su, Zerong Zheng et al.SIGGRAPH 2024 · 27 citations
- DRiVE: Diffusion-based Rigging Empowers Generation of Versatile and Expressive CharactersMingze Sun, Junhao Chen, Junting Dong, Yurun Chen et al.CVPR 2025
- SemanticGarment: Semantic-Controlled Generation and Editing of 3D Gaussian GarmentsRuiyan Wang, Zhengxue Cheng, Zonghao Lin, Jun Ling et al.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 et al.SIGGRAPH 2021 · 35 citations
