Research map / Video / Video generation
Pantheon360: Taming Digital Twin Generation via 3D-Aware 360deg Video Diffusion
Ting-Hsuan Chen, Ying-Huan Chen, Tao Tu, Jie-Ying Lee, Cho-Ying Wu, Fangzhou Lin, Hengyuan Zhang, David Paz, Xinyu Huang, Yuliang Guo, Yu-Lun Liu, Yue Wang and 1 more
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 the explicit 3D Cache geometric condition V_geo (ablation) | Pantheon360 · Web360 | MET3R: 0.523 -> 0.284 | Improved |
| add the explicit 3D Cache geometric condition V_geo (ablation) | Pantheon360 · Habitat | PSNR: 14.22 -> 20.39 | Improved |
| keep more 3D Cache points (50% dropped vs none) (ablation) | Pantheon360 · Web360 | PSNR: 20.76 -> 22.84 | Improved |
| add dual-anchor conditioning (start and end frames) over single anchor (ablation) | Pantheon360 · Google Street View interpolation | PSNR: 20.921 -> 27.860 | Improved |
| add latent fusion to dual-anchor model (ablation) | Pantheon360 dual-anchor · Google Street View interpolation | PSNR: 27.860 -> 28.948 | Improved |
| add latent fusion to dual-anchor model (ablation) | Pantheon360 dual-anchor · Google Street View interpolation | IE: 8.120 -> 7.437 | Improved |
| add latent fusion to single-anchor model (ablation) | Pantheon360 single-anchor · Google Street View interpolation | IE: 4.784 -> 12.083 | Hurt |
| add latent fusion to single-anchor model (ablation) | Pantheon360 single-anchor · Google Street View interpolation | PSNR: 20.921 -> 28.006 | Improved |
| use single-anchor instead of dual-anchor (ablation) | Pantheon360 · Google Street View interpolation | STWE: 0.395 -> 0.124 | Improved |
| render the 360 geometric scaffold into 360 diffusion instead of perspective baselines (GEN3C) | 360 video generation · Habitat | MET3R: 0.4522 -> 0.3026 | Improved |
Closest papers by meaning
- GEN3C: 3D-Informed World-Consistent Video Generation with Precise Camera Control (CVPR 2025 · similarity 0.88)
- SynCamMaster: Synchronizing Multi-Camera Video Generation from Diverse Viewpoints (ICLR 2025 · similarity 0.88)
- Collaborative Video Diffusion: Consistent Multi-video Generation with Camera Control (NeurIPS 2024 · similarity 0.87)
- HarmonyView: Harmonizing Consistency and Diversity in One-Image-to-3D (CVPR 2024 · similarity 0.87)
- Imagine360: Immersive 360 Video Generation from Perspective Anchor (NeurIPS 2025 · similarity 0.87)
- Diffusion4D: Fast Spatial-temporal Consistent 4D generation via Video Diffusion Models (NeurIPS 2024 · 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.
