Research map / 3D vision / 3D generation
CaliTex: Geometry-Calibrated Attention for View-Coherent 3D Texture Generation
Chenyu Liu, Hongze Chen, Jingzhi Bao, Lingting Zhu, Runze Zhang, Weikai Chen, Zeyu Hu, Yingda Yin, Keyang Luo, Xin Wang
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 |
|---|---|---|---|
| add Part-Aligned Attention (ablation) | CaliTex · Multi-view alignment | MV-MSE: 0.0415 -> 0.0384 | Improved |
| add Condition-Routed Attention (ablation) | CaliTex · Multi-view alignment | MV-MSE: 0.0403 -> 0.0384 | Improved |
| CaliTex versus best open-source baseline MV-Adapter | image-to-texture generation · Objaverse + game assets texture eval | FID: 169.4 -> 157.8 | Improved |
| CaliTex versus best baseline on LPIPS | image-to-texture generation · Objaverse + game assets texture eval | LPIPS: 0.2939 -> 0.2508 | Improved |
| CaliTex versus best baseline in user study quality | image-to-texture generation · User study (25 participants) | Qual: 3.10 -> 4.53 | Improved |
| remove Part-Aligned Attention (qualitative) (ablation) | CaliTex · Qualitative ablation | cross-view artifacts | Improved |
Closest papers by meaning
- Aligned Novel View Image and Geometry Synthesis via Cross-modal Attention Instillation (ICLR 2026 · similarity 0.89)
- DreamCraft3D: Hierarchical 3D Generation with Bootstrapped Diffusion Prior (ICLR 2024 · similarity 0.87)
- Cue3D: Quantifying the Role of Image Cues in Single-Image 3D Generation (NeurIPS 2025 · similarity 0.87)
- TexTailor: Customized Text-aligned Texturing via Effective Resampling (ICLR 2025 · similarity 0.87)
- Pygmalion Effect in Vision: Image-to-Clay Translation for Reflective Geometry Reconstruction (NeurIPS 2026 · similarity 0.86)
- FlexiTex: Enhancing Texture Generation via Visual Guidance (AAAI 2025 · similarity 0.86)
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.
