Research map / Video / Video generation
Beyond the Frame: Generating 360deg Panoramic Videos from Perspective Videos
Rundong Luo, Matthew Wallingford, Ali Fahardi, Noah Snavely, Wei-Chiu Ma
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 view-based frame alignment (ablation) | Argus · Video-to-360 ablation | PSNR: 20.42 -> 21.83 | Improved |
| add view-based frame alignment (ablation) | Argus · Video-to-360 ablation | FVD: 1349.6 -> 1228.6 | Improved |
| add view-based frame alignment (ablation) | Argus · Video-to-360 ablation | Imaging quality: 0.3816 -> 0.4939 | Improved |
| add view-based frame alignment (ablation) | Argus · Video-to-360 ablation | LPIPS: 0.3194 -> 0.2409 | Improved |
| add blended decoding (ablation) | Argus · Video-to-360 ablation | LPIPS: 0.2675 -> 0.2409 | Improved |
| add blended decoding (ablation) | Argus · Video-to-360 ablation | Imaging quality: 0.4574 -> 0.4939 | Improved |
| add blended decoding (ablation) | Argus · Video-to-360 ablation | PSNR: 22.09 -> 21.83 | Hurt |
| add blended decoding (ablation) | Argus · Video-to-360 ablation | FVD: 1226.3 -> 1228.6 | No clear effect |
| use Argus instead of adapted PanoDiffusion | PanoDiffusion · Video-to-360 (real trajectory) | FVD: 2649.0 -> 1228.6 | Improved |
| use Argus instead of adapted PanoDiffusion | PanoDiffusion · Video-to-360 (line consistency) | Line consistency: 0.6504 -> 0.8506 | Improved |
| use Argus instead of Follow-Your-Canvas outpainting | Follow-Your-Canvas · Outpainting comparison (FoV 120) | Imaging quality: 0.4130 -> 0.4895 | Improved |
| use Argus instead of Follow-Your-Canvas outpainting | Follow-Your-Canvas · Outpainting comparison (FoV 60) | Aesthetic quality: 0.4750 vs 0.4722 | No clear effect |
Closest papers by meaning
- ViewPoint: Panoramic Video Generation with Pretrained Diffusion Models (NeurIPS 2025 · similarity 0.92)
- Imagine360: Immersive 360 Video Generation from Perspective Anchor (NeurIPS 2025 · similarity 0.91)
- PanoWorld: Geometry-Consistent Panoramic Video World Modeling (NeurIPS 2026 · similarity 0.91)
- PanoWan: Lifting Diffusion Video Generation Models to 360$^\circ$ with Latitude/Longitude-aware Mechanisms (NeurIPS 2025 · similarity 0.89)
- DynamicScaler: Seamless and Scalable Video Generation for Panoramic Scenes (CVPR 2025 · similarity 0.88)
- 4K4DGen: Panoramic 4D Generation at 4K Resolution (ICLR 2025 · 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.
