Research map / Image generation / Text-to-image diffusion
Text-Image Conditioned 3D Generation
Jiazhong Cen, Jiemin Fang, Sikuang Li, Guanjun Wu, Chen Yang, Taoran Yi, Zanwei Zhou, Zhikuan Bao, Lingxi Xie, Wei Shen, Qi Tian
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 |
|---|---|---|---|
| fuse image- and text-conditioned predictions (SimFusion) instead of image-only on a low-information view | UniLat3D · Toys4K View-1 | FD_DINOv2: 125.93 -> 82.40 | Improved |
| add cross-modal bridges with joint fine-tuning (ablation) | TIGON · Toys4K | FD_DINOv2: 66.78 -> 61.59 | Improved |
| joint fine-tuning without bridges (ablation) | TIGON · Toys4K | FD_DINOv2: 66.78 -> 66.04 | No clear effect |
| learned adaptive-weight late fusion instead of averaging (ablation) | TIGON · Toys4K | FD_DINOv2: 61.59 -> 60.90 | No clear effect |
| attention-based late fusion instead of averaging (ablation) | TIGON · Toys4K | FD_DINOv2: 61.59 -> 62.00 | No clear effect |
| use a less informative reference view (View-1 instead of View-0) | TRELLIS (GS) · Toys4K | FD_DINOv2: 56.08 -> 143.58 | Hurt |
| add text conditioning to image conditioning (TIGON vs UniLat3D image-only, 3DGS) | UniLat3D · Toys4K | FD_DINOv2: 85.30 -> 61.59 | Improved |
| TIGON fine-tuning on single-modality input vs UniLat3D baseline (image only) | TIGON · Toys4K | FD_DINOv2: 85.30 -> 84.62 | No clear effect |
Closest papers by meaning
- VP3D: Unleashing 2D Visual Prompt for Text-to-3D Generation (CVPR 2024 · similarity 0.89)
- ViewDiff: 3D-Consistent Image Generation with Text-to-Image Models (CVPR 2024 · similarity 0.88)
- Let Language Constrain Geometry: Vision–Language Models as Semantic and Spatial Critics for 3D Generation (ICML 2026 · similarity 0.87)
- Learning Visual Generative Priors without Text (CVPR 2025 · similarity 0.87)
- IT3D: Improved Text-to-3D Generation with Explicit View Synthesis (AAAI 2024 · similarity 0.87)
- Sculpt3D: Multi-View Consistent Text-to-3D Generation with Sparse 3D Prior (CVPR 2024 · similarity 0.87)
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.
