Research map / Video / Video generation
PanoWorld-X: Generating Explorable Panoramic Worlds via Sphere-Aware Video Diffusion
Yuyang Yin, Hao-Xiang Guo, Fangfu Liu, Mengyu Wang, Hanwen Liang, Eric Li, Yikai Wang, Xiaojie Jin, Yao Zhao, Yunchao Wei
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 Sphere-Aware Attention (ablation) | PanoWorld-X · PanoExplorer test (ablation) | PSNR: 17.59 -> 19.34 | Improved |
| add Sphere-Aware Attention (ablation) | PanoWorld-X · PanoExplorer test (ablation) | FID: 29.96 -> 28.01 | Improved |
| add Sphere-Aware Attention (ablation) | PanoWorld-X · PanoExplorer test (ablation) | FVD: 492.98 -> 467.18 | Improved |
| add Sphere-Aware Attention (ablation) | PanoWorld-X · PanoExplorer test (ablation) | R_err: 0.069 -> 0.061 | Improved |
| add exploration-aware controllable branch (ablation) | PanoWorld-X · PanoExplorer test (ablation) | T_err: 0.152 -> 0.073 | Improved |
| add exploration-aware controllable branch (ablation) | PanoWorld-X · PanoExplorer test (ablation) | R_err: 0.102 -> 0.061 | Improved |
| add exploration-aware controllable branch (ablation) | PanoWorld-X · PanoExplorer test (ablation) | PSNR: 16.30 -> 19.34 | Improved |
| add data position normalization (10 cm stride) (ablation) | PanoWorld-X · PanoExplorer test (ablation) | R_err: 0.114 -> 0.061 | Improved |
| add data position normalization (10 cm stride) (ablation) | PanoWorld-X · PanoExplorer test (ablation) | T_err: 0.102 -> 0.073 | Improved |
| add data position normalization (10 cm stride) (ablation) | PanoWorld-X · PanoExplorer test (ablation) | FID: 40.37 -> 28.01 | Improved |
| use PanoWorld-X instead of GenEX | panoramic video generation · PanoExplorer test | FVD: 1113.72 -> 467.18 | Improved |
| use PanoWorld-X Perspective instead of AC3D | camera-controllable generation · cropped perspective views | T_err: 0.087 -> 0.073 | 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.
- Imagine360 — Imagine360: Immersive 360 Video Generation from Perspective Anchor (NeurIPS 2025) · 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
- PanoWorld: Geometry-Consistent Panoramic Video World Modeling (NeurIPS 2026 · similarity 0.92)
- ViewPoint: Panoramic Video Generation with Pretrained Diffusion Models (NeurIPS 2025 · similarity 0.90)
- DynamicScaler: Seamless and Scalable Video Generation for Panoramic Scenes (CVPR 2025 · similarity 0.89)
- PanoWan: Lifting Diffusion Video Generation Models to 360$^\circ$ with Latitude/Longitude-aware Mechanisms (NeurIPS 2025 · similarity 0.89)
- 4K4DGen: Panoramic 4D Generation at 4K Resolution (ICLR 2025 · similarity 0.89)
- DiffPano: Scalable and Consistent Text to Panorama Generation with Spherical Epipolar-Aware Diffusion (NeurIPS 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.
