Research map / 3D vision / 3D generation
Single Image to Textured 3D Object Generation in Frequency Domain: From Theory to Pipeline
Qisen Wang, Yifan Zhao, Jia Li
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 high-pass 2D prior guidance (frequency bound r=0.6) to the 3D prior (ablation) | Morpheus3D · Realfusion15 | CLIPIQA: 0.707 -> 0.748 | Improved |
| add high-pass 2D prior guidance (r=0.6) (ablation) | Morpheus3D · Realfusion15 | MANIQA: 0.433 -> 0.454 | Improved |
| add high-pass 2D prior guidance (r=0.6) (ablation) | Morpheus3D · MorpheusObj30 | CLIP-Similarity: 0.816 -> 0.835 | Improved |
| use high-pass filtering (r=0.6) instead of full-pass 2D prior (ablation) | Morpheus3D · Realfusion15 | MANIQA: 0.401 -> 0.454 | Improved |
| use high-pass filtering (r=0.6) instead of full-pass 2D prior (ablation) | Morpheus3D · MorpheusObj30 | MANIQA: 0.438 -> 0.487 | Improved |
| vary frequency bound r across the middle range 0.2 to 0.8 (ablation) | Morpheus3D · Realfusion15 | CLIP-Similarity: 0.824 -> 0.838 | No clear effect |
| increase 2D prior weight k2D from 3.0 to 5.0 (ablation) | Morpheus3D · Realfusion15 | CLIPIQA: 0.748 -> 0.763 | No clear effect |
| add the 2D prior with weight k2D=1.0 versus none (ablation) | Morpheus3D · Realfusion15 | CLIP-Similarity: 0.824 -> 0.835 | Improved |
| use Morpheus3D instead of Magic123 | Morpheus3D · MorpheusObj30 | MANIQA: 0.315 -> 0.487 | Improved |
| use Morpheus3D instead of Magic123 | Morpheus3D · Realfusion15 | MANIQA: 0.316 -> 0.454 | Improved |
| use Morpheus3D instead of Magic123 for training cost | Morpheus3D · banana case | training time (minutes): 341.083 -> 111.981 | Improved |
| fine-tune the 3D prior with LoRA (VSD) instead of using SDS (ablation) | Morpheus3D · MorpheusObj30 | reconstruction quality | Hurt |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 on most shared results.
- Magic123 — Magic123: One Image to High-Quality 3D Object Generation Using Both 2D and 3D Diffusion Priors (ICLR 2024) · better on 10 of 10 shared results
- RealFusion — RealFusion: 360deg Reconstruction of Any Object From a Single Image (CVPR 2023) · 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
- One-2-3-45++: Fast Single Image to 3D Objects with Consistent Multi-View Generation and 3D Diffusion (CVPR 2024 · similarity 0.92)
- Wonder3D: Single Image to 3D using Cross-Domain Diffusion (CVPR 2024 · similarity 0.90)
- Cycle3D: High-quality and Consistent Image-to-3D Generation via Generation-Reconstruction Cycle (AAAI 2025 · similarity 0.90)
- Magic123: One Image to High-Quality 3D Object Generation Using Both 2D and 3D Diffusion Priors (ICLR 2024 · similarity 0.90)
- Diffusion$^2$: Dynamic 3D Content Generation via Score Composition of Video and Multi-view Diffusion Models (ICLR 2025 · similarity 0.90)
- DreamCraft3D: Hierarchical 3D Generation with Bootstrapped Diffusion Prior (ICLR 2024 · similarity 0.90)
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.
