直接在球面投影域实现全景图统一编辑，解决几何失真与一致性问题。
World-Shaper: A Unified Framework for 360° Panoramic Editing
- 在等距柱状投影域设计统一编辑框架，避免立方体贴图的结构断裂。
- 在PEBench上实现更优几何一致性与文本控制能力，优于现有最佳方法。
- 适合需要高质量全景生成与灵活编辑的虚拟现实、数字孪生开发者。
能够编辑全景图像对构建真实的360°视觉体验至关重要。然而，现有基于透视图的编辑方法无法建模全景的空间结构；传统立方体贴图分解虽试图克服此问题，但因不匹配球面几何而破坏全局一致性。受此启发，我们直接在等距柱状投影（ERP）域重述全景编辑，并提出World-Shaper——一个统一的几何感知框架，将全景生成与编辑整合于单一以编辑为中心的设计中。为应对配对数据稀缺，采用生成-再编辑范式，利用可控全景生成作为辅助阶段，合成多样化配对样本用于监督学习。为缓解几何畸变，引入几何感知学习策略，显式施加位置感知形状监督，并通过渐进训练隐式内化全景先验。在新基准PEBench上的大量实验表明，该方法在几何一致性、编辑保真度和文本可控性上均优于当前最优方法，实现统一控制下的连贯且灵活的360°视觉世界创作。代码、模型与数据将在项目页面公开：https://world-shaper-project.github.io/
原文摘要 · Abstract (English)
Being able to edit panoramic images is crucial for creating realistic 360° visual experiences. However, existing perspective-based image editing methods fail to model the spatial structure of panoramas. Conventional cube-map decompositions attempt to overcome this problem but inevitably break global consistency due to their mismatch with spherical geometry. Motivated by this insight, we reformulate panoramic editing directly in the equirectangular projection (ERP) domain and present World-Shaper, a unified geometry-aware framework that bridges panoramic generation and editing within a single editing-centric design. To overcome the scarcity of paired data, we adopt a generate-then-edit paradigm, where controllable panoramic generation serves as an auxiliary stage to synthesize diverse paired examples for supervised editing learning. To address geometric distortion, we introduce a geometry-aware learning strategy that explicitly enforces position-aware shape supervision and implicitly internalizes panoramic priors through progressive training. Extensive experiments on our new benchmark, PEBench, demonstrate that our method achieves superior geometric consistency, editing fidelity, and text controllability compared to SOTA methods, enabling coherent and flexible 360° visual world creation with unified editing control. Code, model, and data will be released at our project page: https://world-shaper-project.github.io/
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。