Research map / Image generation / Text-to-image diffusion
Instant3D: Instant Text-to-3D Generation
Ming Li, Pan Zhou, Jiawei Liu, Jussi Keppo, Min Lin, Shuicheng Yan, Xiangyu Xu
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 Gaussian noise in style injection (ablation) | Instant3D · Animals | training stability | Improved |
| add token embeddings in style injection (ablation) | Instant3D · Animals | text-3D consistency | Improved |
| add token-to-plane transformation instead of learnable constant (ablation) | Instant3D · Animals | text-3D alignment | Improved |
| use scaled-sigmoid instead of conventional sigmoid for albedo (ablation) | Instant3D · Animals | training convergence speed | Improved |
| use adaptive Perp-Neg instead of fixed-weight Perp-Neg (ablation) | Instant3D · Animals | Janus problem across objects | Improved |
| compare amortized Instant3D to per-prompt optimization baselines | Instant3D · Animals | iterations per prompt for good CLIP-RP: 10,000 -> 2,000 | Improved |
| compare Instant3D to ProlificDreamer on realism | Instant3D · Animals user study | realism preference (%): 1.74% -> 75.28% | Improved |
| compare Instant3D to ATT3D on realism | Instant3D · ATT3D prompt set | realism preference (%): 8.68% -> 91.32% | Improved |
| compare Instant3D to ATT3D on consistency | Instant3D · ATT3D prompt set | consistency preference (%): 13.23% -> 86.77% | 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.
- DreamFusion — DreamFusion: Text-to-3D using 2D Diffusion (ICLR 2023) · better on 2 of 2 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
- Instant3D: Fast Text-to-3D with Sparse-view Generation and Large Reconstruction Model (ICLR 2024 · similarity 0.93)
- DIRECT-3D: Learning Direct Text-to-3D Generation on Massive Noisy 3D Data (CVPR 2024 · similarity 0.89)
- PI3D: Efficient Text-to-3D Generation with Pseudo-Image Diffusion (CVPR 2024 · similarity 0.89)
- VP3D: Unleashing 2D Visual Prompt for Text-to-3D Generation (CVPR 2024 · similarity 0.88)
- MARVEL-40M+: Multi-Level Visual Elaboration for High-Fidelity Text-to-3D Content Creation (CVPR 2025 · similarity 0.88)
- IT3D: Improved Text-to-3D Generation with Explicit View Synthesis (AAAI 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.
