Research map / 3D vision / Face and shape
T2TD: Text-3D Generation Model Based on Prior Knowledge Guidance
Weizhi Nie, Ruidong Chen, Weijie Wang, Bruno Lepri, Nicu Sebe
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 L_reg to align text feature with shape feature (ablation) | baseline · ShapeNet text-3D ablation | IOU: 9.23 -> 12.20 | Improved |
| add L_ae to end-to-end finetune on top of L_reg (ablation) | +L_reg · ShapeNet text-3D ablation | FPD: 111.43 -> 51.12 | Improved |
| add attribute prior (ablation) | +L_reg +L_ae · ShapeNet text-3D ablation | FPD: 51.12 -> 46.54 | Improved |
| add shape prior (ablation) | +L_reg +L_ae · ShapeNet text-3D ablation | FPD: 51.12 -> 40.35 | Improved |
| add causal model to filter shape prior (ablation) | +shape prior · ShapeNet text-3D ablation | FPD: 40.35 -> 36.22 | Improved |
| add attribute prior on top of causal shape prior (ablation) | +shape prior (Causal) · ShapeNet text-3D ablation | FPD: 36.22 -> 30.71 | Improved |
| use prior fusion module instead of concatenation (ablation) | Concatenate · ShapeNet text-3D prior fusion | IOU: 12.74 -> 14.07 | Improved |
| use prior fusion module instead of average fusion (ablation) | Average Fusion · ShapeNet text-3D prior fusion | FPD: 74.28 -> 40.35 | Improved |
| use prior-knowledge guided T2TD over Text-Guided 3D | Text-Guided · ShapeNet text-3D (chairs and tables) | IOU: 12.21 -> 14.22 | Improved |
| use T2TD over Text2Shape | Text2Shape · ShapeNet text-3D (chairs and tables) | EMD: 0.4443 -> 0.1742 | Improved |
| add prior knowledge on Inception Score | Text-Guided · ShapeNet text-3D (chairs and tables) | IS: 1.97 -> 1.97 | No clear effect |
Closest papers by meaning
- IT3D: Improved Text-to-3D Generation with Explicit View Synthesis (AAAI 2024 · similarity 0.86)
- Let 2D Diffusion Model Know 3D-Consistency for Robust Text-to-3D Generation (ICLR 2024 · similarity 0.86)
- Sculpt3D: Multi-View Consistent Text-to-3D Generation with Sparse 3D Prior (CVPR 2024 · similarity 0.86)
- MARVEL-40M+: Multi-Level Visual Elaboration for High-Fidelity Text-to-3D Content Creation (CVPR 2025 · similarity 0.86)
- ViewDiff: 3D-Consistent Image Generation with Text-to-Image Models (CVPR 2024 · similarity 0.86)
- TextField3D: Towards Enhancing Open-Vocabulary 3D Generation with Noisy Text Fields (ICLR 2024 · 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.
