Research map / 3D vision / 3D generation
SphericalDreamer: Generating Navigable Immersive 3D Worlds with Panorama Fusion
Antoine Schnepf, Karim Kassab, Flavian Vasile, Andrew I. Comport
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 layered depth panoramas (ablation) | SphericalDreamer · Ablation (rotation+translation) | BRISQUE: 45.8937 -> 43.4709 | Improved |
| add layered depth panoramas (ablation) | SphericalDreamer · Ablation (rotation+translation) | Coverage: 0.9652 -> 0.9993 | Improved |
| add layered depth panoramas (ablation) | SphericalDreamer · Ablation (rotation+translation) | Q-Align: 2.1935 -> 2.3660 | Improved |
| add harmonic blending instead of naive blending (ablation) | SphericalDreamer · Ablation (rotation+translation) | BRISQUE: 47.1084 -> 43.4709 | Improved |
| add harmonic blending instead of naive blending (ablation) | SphericalDreamer · Ablation (rotation+translation) | Coverage: 0.9242 -> 0.9993 | Improved |
| add harmonic blending instead of naive blending (ablation) | SphericalDreamer · Ablation (rotation+translation) | Q-Align: 1.9953 -> 2.3660 | Improved |
| add harmonic blending instead of diffusion depth inpainting (ablation) | SphericalDreamer · Ablation (rotation+translation) | BRISQUE: 44.3742 -> 43.4709 | Improved |
| add harmonic blending instead of diffusion depth inpainting (ablation) | SphericalDreamer · Ablation (rotation+translation) | CLIP-IQA: 0.5976 -> 0.7582 | Improved |
| add harmonic blending instead of bilinear interpolation (ablation) | SphericalDreamer · Ablation (rotation+translation) | Coverage: 0.9835 -> 0.9993 | Improved |
| add harmonic blending instead of bilinear interpolation (ablation) | SphericalDreamer · Ablation (rotation+translation) | Q-Align: 2.2595 -> 2.3660 | Improved |
| increase world size from N=3 to N=7 panoramas (ablation) | SphericalDreamer · World size sweep | BRISQUE: 43.4683 -> 41.5514 | No clear effect |
| increase world size from N=3 to N=7 panoramas (ablation) | SphericalDreamer · World size sweep | Q-Align: 2.3662 -> 2.3490 | No clear effect |
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.
- LucidDreamer — LucidDreamer: Towards High-Fidelity Text-to-3D Generation via Interval Score Matching (CVPR 2024) · better on 6 of 6 shared results
- SceneScape — SceneScape: Text-Driven Consistent Scene Generation (NeurIPS 2023) · better on 6 of 6 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
- HORIZON: High-Resolution Semantically Controlled Panorama Synthesis (AAAI 2024 · similarity 0.87)
- 4K4DGen: Panoramic 4D Generation at 4K Resolution (ICLR 2025 · similarity 0.86)
- ViewPoint: Panoramic Video Generation with Pretrained Diffusion Models (NeurIPS 2025 · similarity 0.85)
- PanoWorld: Geometry-Consistent Panoramic Video World Modeling (NeurIPS 2026 · similarity 0.85)
- DiffPano: Scalable and Consistent Text to Panorama Generation with Spherical Epipolar-Aware Diffusion (NeurIPS 2024 · similarity 0.85)
- WonderWorld: Interactive 3D Scene Generation from a Single Image (CVPR 2025 · similarity 0.85)
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.
