Research map / 3D vision / Face and shape
Image-Guided Geometric Stylization of 3D Meshes
Changwoon Choi, Hyunsoo Lee, Clément Jambon, Yael Vinker, Young Min Kim
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 approximated VAE encoder instead of the original SDXL VAE (ablation) | Ours · Geometric stylization (qualitative) | deformation quality | Improved |
| add cage coefficient regularization (ablation) | Ours · Geometric stylization (qualitative) | deformation quality | Improved |
| add symmetry loss (ablation) | Ours · Geometric stylization (qualitative) | deformation consistency | Improved |
| use SDXL with approximated VAE encoder instead of SDXL with original VAE or DeepFloyd-IF (ablation) | SDS text-guided mesh deformation · Text-guided mesh deformation (qualitative) | semantic alignment of deformation | Improved |
| use proposed method instead of MeshUp | Geometric stylization · Geometric stylization (12 meshes, 16 views) | FID: 396.23 -> 376.57 | Improved |
| use proposed method instead of TextDeformer | Geometric stylization · Geometric stylization (12 meshes, 16 views) | FID: 400.58 -> 376.57 | Improved |
| use proposed method instead of baselines in user study | Geometric stylization · User study (32 participants, 8 samples) | geometric alignment and aesthetic style transfer ranking | Mixed |
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.
- Text2Mesh — Text2Mesh: Text-Driven Neural Stylization for Meshes (CVPR 2022) · better on 1 of 1 shared result
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
- Styl3R: Instant 3D Stylized Reconstruction for Arbitrary Scenes and Styles (NeurIPS 2025 · similarity 0.91)
- Geometry in Style: 3D Stylization via Surface Normal Deformation (CVPR 2025 · similarity 0.90)
- LeGO: Leveraging a Surface Deformation Network for Animatable Stylized Face Generation with One Example (CVPR 2024 · similarity 0.90)
- 3DToonify: Creating Your High-Fidelity 3D Stylized Avatar Easily from 2D Portrait Images (CVPR 2024 · similarity 0.89)
- Morpheus: Text-Driven 3D Gaussian Splat Shape and Color Stylization (CVPR 2025 · similarity 0.88)
- ReGS: Reference-based Controllable Scene Stylization with Gaussian Splatting (NeurIPS 2024 · similarity 0.88)
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.
