让AI生成无缝360度全景图，支持写实与风格化场景。
SHERPA: Seam-aware Harmonized ERP Adaptation for Open-Domain 360$^\circ$ Panorama Generation
- 用频段选择性环形位置编码修复全景图接缝问题。
- 在真实和风格化提示下均生成无接缝的360°全景图。
- 适合需要高质量全景生成的虚拟现实与游戏开发人员。
全景图像在世界构建、游戏和仿真中应用日益广泛，用户不仅需要逼真的场景，还需风格化或非写实环境。大规模文本到图像扩散模型和流模型虽具备丰富的风格与语义先验，但平面图像训练方式与等距圆柱投影（ERP）中360°全景图的环绕拓扑及极区存在偏差。本文提出SHERPA，一种轻量级适应框架，结合频段选择性环形位置编码（Circular RoPE）、环形潜在编码/解码、图像侧FFN适配器与双路径训练策略。环形位置编码仅替换对缝合敏感的高频水平部分，保留预训练低频谱。成对全景路径监督几何结构，非成对风格路径通过自监督航向一致性实现目标无关风格化提示。结果表明，SHERPA可在写实全景域与开放域风格化提示下生成高质量360°全景图。
原文摘要 · Abstract (English)
Panoramic imagery is increasingly used in world-generation, games, and simulation, where users may need not only photorealistic scenes but also stylized and non-photorealistic environments. Large-scale text-to-image diffusion and flow models provide broad style and semantic priors for this goal, but planar image training misaligns them with the wrap-around topology and polar regions of $360^\circ$ panoramas represented in equirectangular projection (ERP). We present SHERPA, a lightweight adaptation framework that combines frequency-selective Circular RoPE, Circular Latent Encoding/Decoding, image-side FFN adapters, and a Dual-Path Training Scheme. Circular RoPE replaces only the seam-sensitive high-frequency horizontal RoPE band with integer-periodic harmonics while preserving the pretrained lower-frequency spectrum. The Paired Panorama Path supervises geometry, while the Unpaired Style Path uses self-supervised yaw consistency for target-free stylized prompts. As a result, SHERPA generates $360^\circ$ panoramas across both photorealistic panorama domains and open-domain stylized prompts.
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。