Research map / 3D vision / 3D generation
Automatic Content-Aware Projection for 360deg Videos
Yeong Won Kim, Chang-Ryeol Lee, Dae-Yong Cho, Yong Hoon Kwon, Hyeok-Jae Choi, Kuk-Jin Yoon
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 model interpolation to optimized Pannini (ablation) | content-aware projection · user study | average votes: 37.62 -> 45.05 | Improved |
| add model interpolation to optimized Pannini (ablation) | content-aware projection · synthetic images 16:9 conformality | conformality: 0.5848 -> 0.7539 | Improved |
| add model interpolation to optimized Pannini (ablation) | content-aware projection · synthetic images 21:9 conformality | conformality: 0.6011 -> 0.8407 | Improved |
| add model interpolation to optimized Pannini (ablation) | content-aware projection · synthetic images 16:9 straightness | straightness: 0.9995 -> 0.9705 | Hurt |
| add model interpolation to optimized Pannini (ablation) | content-aware projection · synthetic images 21:9 straightness | straightness: 0.9999 -> 0.9874 | Hurt |
| use proposed projection instead of rectilinear | projection · user study | average votes: 19.57 -> 45.05 | Improved |
| use proposed projection instead of Pannini d=1.0 | projection · synthetic images 21:9 conformality | conformality: 0.8763 -> 0.8407 | Hurt |
| use proposed projection instead of Pannini d=0.5 | projection · user study | average votes: 42.76 -> 45.05 | Improved |
| use proposed projection instead of Pannini d=1.0 | projection · synthetic images 16:9 straightness | straightness: 0.9639 -> 0.9705 | Improved |
| lower Pannini d from 1.0 to 0.5 | Pannini projection · synthetic images 16:9 straightness | straightness: 0.9639 -> 0.9748 | Improved |
Closest papers by meaning
- Imagine360: Immersive 360 Video Generation from Perspective Anchor (NeurIPS 2025 · similarity 0.83)
- 360DVD: Controllable Panorama Video Generation with 360-Degree Video Diffusion Model (CVPR 2024 · similarity 0.82)
- ViewPoint: Panoramic Video Generation with Pretrained Diffusion Models (NeurIPS 2025 · similarity 0.82)
- MVSplat360: Feed-Forward 360 Scene Synthesis from Sparse Views (NeurIPS 2024 · similarity 0.81)
- Pseudo-Generalized Dynamic View Synthesis from a Video (ICLR 2024 · similarity 0.81)
- Cavia: Camera-controllable Multi-view Video Diffusion with View-Integrated Attention (ICML 2025 · similarity 0.81)
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.
