无需训练和优化，直接生成360全景图，效果媲美主流模型。
SpheRoPE: Zero-Shot Optimization-Free 360 Panorama Generation with Spherical RoPE
- 用球面旋转位置编码替代原位置编码，天然建模球面结构。
- 在文本到全景生成中达到与微调模型相当的视觉质量。
- 兼容多种主流模型，适合快速部署360内容生成场景。
我们提出一种零样本、无需训练且无需优化的框架，通过直接注入球面先验，生成360度全景图像与视频。现有方法要么依赖稀缺全景数据的昂贵微调，限制泛化能力；要么采用多步优化，导致推理延迟过高。我们发现当前生成模型虽在大规模训练中具备部分全景先验，但因无法满足等距圆柱投影（ERP）的拓扑约束而表现不足。为此，我们引入一种零样本、无优化的方法，在推理时解决该约束：球面旋转位置编码（Spherical RoPE）将低频通道重参数化为3D笛卡尔坐标，以自然编码球面流形，高频通道则进行谐波量化以确保精确周期性。结合互补的语义畸变分类器自由引导（CFG），显式控制几何结构，避免重训练，并保留先进模型的全部创作潜力。该方法适用于多种骨干网络与360生成模态。我们在Flux.1、Flux.2和LTX-Video骨干上验证了文本到全景生成任务，性能优于基线，全程保持训练自由。
原文摘要 · Abstract (English)
We present a zero-shot, training-free and optimization-free framework for generating 360 panoramic images and videos by directly injecting spherical priors into pre-trained diffusion transformers. Existing methods either rely on costly fine-tuning on scarce panoramic data that limits generalization, or leverage multi-step optimization that incurs prohibitive inference latency. We observe that contemporary generative models natively exhibit some panoramic priors from large-scale training. However, these emergent capabilities are insufficient, as the models fundamentally fail to satisfy the rigorous topological constraints imposed by equirectangular projection (ERP). We introduce a zero-shot and optimization-free approach that resolves these constraints at inference time. Spherical RoPE replaces standard rotary position embeddings: low-frequency channels are re-parameterized as 3D Cartesian coordinates to natively encode the spherical manifold, while high-frequency channels are harmonically quantized to enforce exact periodicity. Coupled with complementary Semantic Distortion classifier-free guidance (CFG) that explicitly steers geometry, we avoid retraining and inherit the full creative breadth of state-of-the-art models. Our approach generalizes across diverse backbones and 360 generation modalities. We demonstrate this across text-to-panorama using Flux.1, Flux.2, and LTX-Video backbones, achieving competitive performance against baselines, all while remaining training-free. Project page: https://orhir.github.io/SpheRoPE
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。