Research map / Image generation / Text-to-image diffusion
DiT360: High-Fidelity Panoramic Image Generation via Hybrid Training
Haoran Feng, Dizhe Zhang, Xiangtai Li, Bo Du, Lu Qi
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 position-aware circular padding (ablation) | Flux + LoRA · Matterport3D val text-to-panorama | FID: 46.69 -> 43.71 | Improved |
| add position-aware circular padding (ablation) | Flux + LoRA · Matterport3D val text-to-panorama | BRISQUE: 17.02 -> 13.61 | Improved |
| add distortion-aware cube loss (ablation) | Flux + LoRA · Matterport3D val text-to-panorama | FID_pole: 66.03 -> 60.16 | Improved |
| add distortion-aware cube loss (ablation) | Flux + LoRA · Matterport3D val text-to-panorama | IS: 1.51 -> 1.57 | Improved |
| add rotation-consistent yaw loss (ablation) | Flux + LoRA · Matterport3D val text-to-panorama | FAED: 3.23 -> 2.98 | Improved |
| add yaw loss (ablation) | Flux + LoRA · Matterport3D val text-to-panorama | QA_quality: 4.40 -> 4.37 | No clear effect |
| add perspective image guidance (ablation) | Flux + LoRA · Matterport3D val text-to-panorama | FID: 46.69 -> 46.03 | No clear effect |
| add perspective image guidance (ablation) | Flux + LoRA · Matterport3D val text-to-panorama | QA_aesthetic: 3.97 -> 4.02 | Improved |
| combine all four modules (ablation) | Flux + LoRA · Matterport3D val text-to-panorama | FID: 46.69 -> 42.88 | Improved |
| combine all four modules (ablation) | Flux + LoRA · Matterport3D val text-to-panorama | FID_pole: 66.03 -> 50.88 | Improved |
| combine all four modules (ablation) | Flux + LoRA · Matterport3D val text-to-panorama | BRISQUE: 17.02 -> 10.25 | Improved |
| hybrid DiT360 vs best prior (SMGD) | Flux + LoRA · Matterport3D val text-to-panorama | FID: 46.72 -> 42.88 | Improved |
Closest papers by meaning
- DiffPano: Scalable and Consistent Text to Panorama Generation with Spherical Epipolar-Aware Diffusion (NeurIPS 2024 · similarity 0.89)
- Conditional Panoramic Image Generation via Masked Autoregressive Modeling (NeurIPS 2025 · similarity 0.88)
- ViewPoint: Panoramic Video Generation with Pretrained Diffusion Models (NeurIPS 2025 · similarity 0.88)
- Splatter-360: Generalizable 360 Gaussian Splatting for Wide-baseline Panoramic Images (CVPR 2025 · similarity 0.88)
- 4K4DGen: Panoramic 4D Generation at 4K Resolution (ICLR 2025 · similarity 0.87)
- PanoWorld: Geometry-Consistent Panoramic Video World Modeling (NeurIPS 2026 · 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.
