Research map / 3D vision / Face and shape
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
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| use InterCoser instead of STDGEN, CharacterGen or LGM for single-image 3D character generation | InterCoser · VRoid test | FID: 205.68 (best baseline) -> 184.24 | Improved |
| use InterCoser instead of LGM on SSIM | InterCoser · VRoid test | SSIM: 0.5632 -> 0.5643 | No clear effect |
| use geometry-prior-guided GS reconstruction instead of baselines | InterCoser · VRoid test (normal maps) | Sobel: 0.0417 (LGM) -> 0.0397 | Improved |
| add decoupled MVD with masked noise injection and 3D Matching Module to SDM network (ablation) | SDM network · sketch-based layered editing | qualitative alignment | Improved |
| add GS Object ID mechanism to part-level editing (ablation) | part-level interactive editing · GS part-level edit | qualitative edit confinement | Improved |
| add joint local-global SDS optimization to part-level editing (ablation) | part-level interactive editing · GS part-level edit | qualitative semantic consistency | Improved |
| constrain Gaussian means to mesh faces as convex combinations (ablation) | geometry-prior-guided GS reconstruction · GS reconstruction | qualitative artifacts | Improved |
| add normal supervision and smoothness losses on Gaussians (ablation) | geometry-prior-guided GS reconstruction · GS reconstruction | qualitative surface quality | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- STDGEN — StdGEN: Semantic-Decomposed 3D Character Generation from Single Images (CVPR 2025) · better on 6 of 6 shared results
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- 3DitScene: Editing Any Scene via Language-guided Disentangled Gaussian Splatting (ICLR 2025 · similarity 0.86)
- Interactive3D: Create What You Want by Interactive 3D Generation (CVPR 2024 · similarity 0.86)
- DRiVE: Diffusion-based Rigging Empowers Generation of Versatile and Expressive Characters (CVPR 2025 · similarity 0.85)
- Text-Guided 3D Face Synthesis - From Generation to Editing (CVPR 2024 · similarity 0.85)
- DAGSM: Disentangled Avatar Generation with GS-enhanced Mesh (CVPR 2025 · similarity 0.85)
- 3DGS-Drag: Dragging Gaussians for Intuitive Point-Based 3D Editing (ICLR 2025 · similarity 0.84)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
