Research map / Image generation / Editing and style transfer
World-Shaper: A Unified Framework for 360° Panoramic Editing
Dong Liang, Yuhao LIU, Jinyuan Jia, Youjun Zhao, Rynson W. H. Lau
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 distortion-aware attention modulation and layered shape loss together (ablation) | World-Shaper · PEBench panorama editing | VIEScore Overall: 5.32 -> 8.01 | Improved |
| add distortion-aware attention modulation and layered shape loss together (ablation) | World-Shaper · PEBench panorama editing | FID: 58.32 -> 45.25 | Improved |
| add distortion-aware attention modulation (DAAM) alone (ablation) | World-Shaper · PEBench panorama editing | VIEScore Overall: 5.32 -> 7.45 | Improved |
| add layered shape loss (LSL) alone (ablation) | World-Shaper · PEBench panorama editing | VIEScore Overall: 5.32 -> 7.38 | Improved |
| add LSL on top of DAAM (ablation) | World-Shaper · PEBench panorama editing | FID: 53.82 -> 45.25 | Improved |
| add Stage 1 global panorama generation pretraining before Stage 3 editing (ablation) | World-Shaper curriculum · PEBench panorama editing | FID: 52.33 -> 45.25 (with Stage 2 present) | Improved |
| add Stage 2 localized controllable generation before Stage 3 editing (ablation) | World-Shaper curriculum · PEBench panorama editing | CLIP direction score x100: 18.36 -> 19.62 (with Stage 1 present) | Improved |
| add both Stage 1 and Stage 2 versus training Stage 3 directly from Qwen-Image-Edit weights (ablation) | World-Shaper curriculum · PEBench panorama editing | VIEScore Overall: 7.18 -> 8.01 | Improved |
| use ERP-native World-Shaper instead of perspective-based or cube-map editing baselines | panorama editing · PEBench panorama editing | VIEScore Overall: 5.66 (best baseline Qwen) -> 8.01 | Improved |
| use World-Shaper instead of the best baseline in user ranking | panorama editing · PEBench user study (72 participants) | average rank, image quality: 2.37 -> 1.19 | Improved |
| enhance editing prompts with GPT-5 for all methods | all editing methods incl. World-Shaper · PEBench automatic metrics | VIEScore Overall: +0.11 for World-Shaper (8.01 -> 8.12); +0.17 for Qwen | Improved |
| keep the ranking of methods after prompt enhancement | World-Shaper vs baselines · PEBench with enhanced prompts | FID: 45.25 -> 44.65 (-0.60) | No clear effect |
Closest papers by meaning
- PanoWorld: Towards Spatial Supersensing in 360◦ Panorama World (NeurIPS 2026 · similarity 0.88)
- SE360: Semantic Edit in 360° Panoramas via Hierarchical Data Construction (AAAI 2026 · similarity 0.88)
- Splatter-360: Generalizable 360 Gaussian Splatting for Wide-baseline Panoramic Images (CVPR 2025 · similarity 0.86)
- Unified Panoramic Geometry Estimation via Multi-View Foundation Models (NeurIPS 2026 · similarity 0.86)
- PanoWorld: Geometry-Consistent Panoramic Video World Modeling (NeurIPS 2026 · similarity 0.86)
- HORIZON: High-Resolution Semantically Controlled Panorama Synthesis (AAAI 2024 · similarity 0.85)
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.
