用扩散模型直接生成全景图，六面图像统一处理更高效。
CubeDiff: Repurposing Diffusion-Based Image Models for Panorama Generation
- 将全景图拆成六个面，用多视角扩散模型同步生成。
- 无需对应注意力层，仍可生成高质量、高分辨率全景图。
- 支持文本精细控制，适合创意设计与虚拟现实应用。
我们提出一种从文本或图像生成360°全景图的新方法。该方法利用多视角扩散模型，联合生成立方体贴图的六个面。不同于以往依赖等距投影或自回归生成的方法，本方法将每个面视为标准透视图像，简化生成流程并可直接使用现有多视角扩散模型。实验表明，这些模型无需对应感知注意力层即可生成高质量立方体贴图。该方法支持细粒度文本控制，能生成高分辨率全景图，并在训练集外具有良好的泛化能力，定性与定量指标均达到当前最优水平。
原文摘要 · Abstract (English)
We introduce a novel method for generating 360° panoramas from text prompts or images. Our approach leverages recent advances in 3D generation by employing multi-view diffusion models to jointly synthesize the six faces of a cubemap. Unlike previous methods that rely on processing equirectangular projections or autoregressive generation, our method treats each face as a standard perspective image, simplifying the generation process and enabling the use of existing multi-view diffusion models. We demonstrate that these models can be adapted to produce high-quality cubemaps without requiring correspondence-aware attention layers. Our model allows for fine-grained text control, generates high resolution panorama images and generalizes well beyond its training set, whilst achieving state-of-the-art results, both qualitatively and quantitatively. Project page: https://cubediff.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。