Research map / Image generation / Text-to-image diffusion
Dream3D: Zero-Shot Text-to-3D Synthesis Using 3D Shape Prior and Text-to-Image Diffusion Models
Jiale Xu, Xintao Wang, Weihao Cheng, Yan-Pei Cao, Ying Shan, Xiaohu Qie, Shenghua Gao
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 an explicit 3D shape prior to CLIP-guided optimization (ablation) | Dream3D · Text-guided 3D synthesis | CLIP R-Precision (ViT-B/32): 75.47 -> 85.29 | Improved |
| add an explicit 3D shape prior to CLIP-guided optimization (ablation) | Dream3D · Text-guided 3D synthesis | CLIP R-Precision (ViT-B/16): 94.34 -> 98.53 | Improved |
| use Stable Diffusion to bridge text and image rather than generating shape embeddings directly from text embeddings (ablation) | Dream3D text-to-shape generation · Text-to-shape generation | FID: 58.36 -> 40.83 | Improved |
| fine-tune Stable Diffusion to generate rendering-style images (ablation) | Dream3D text-to-shape generation · Text-to-shape generation | FID: 61.88 -> 40.83 | Improved |
| use random-color backgrounds instead of solid-white backgrounds when fine-tuning Stable Diffusion (ablation) | Dream3D text-to-shape generation · Text-to-shape generation | FID: 60.61 -> 33.71 | Improved |
| use random-color backgrounds instead of solid-green backgrounds when fine-tuning Stable Diffusion (ablation) | Dream3D text-to-shape generation · Text-to-shape generation | FID: 71.04 -> 33.71 | Improved |
| retain the shape-prior-preserving loss during CLIP-guided optimization (ablation) | Dream3D · A park bench overgrown with vines | shape-prior structure preservation | 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.
- CLIP-Forge — CLIP-Forge: Towards Zero-Shot Text-To-Shape Generation (CVPR 2022) · better on 3 of 3 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 0.92)
- PI3D: Efficient Text-to-3D Generation with Pseudo-Image Diffusion (CVPR 2024 · similarity 0.91)
- Let 2D Diffusion Model Know 3D-Consistency for Robust Text-to-3D Generation (ICLR 2024 · similarity 0.91)
- DreamTime: An Improved Optimization Strategy for Diffusion-Guided 3D Generation (ICLR 2024 · similarity 0.91)
- HIFA: High-fidelity Text-to-3D Generation with Advanced Diffusion Guidance (ICLR 2024 · similarity 0.91)
- VP3D: Unleashing 2D Visual Prompt for Text-to-3D Generation (CVPR 2024 · similarity 0.91)
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.
