SHERPA: 面向开放域360°全景生成的无缝感知协调ERP适配
SHERPA: Seam-aware Harmonized ERP Adaptation for Open-Domain 360$^\circ$ Panorama Generation
AI总结：
提出SHERPA框架，通过频率选择性圆形RoPE、圆形潜编码/解码、图像侧FFN适配器和双路径训练方案，实现从平面扩散模型到360°全景的轻量级适配，支持逼真和风格化全景生成。
摘要：
全景图像越来越多地用于世界生成、游戏和仿真中，用户不仅需要逼真的场景，还需要风格化和非逼真的环境。大规模文本到图像扩散和流模型为此目标提供了广泛的风格和语义先验，但平面图像训练使它们与等距柱状投影（ERP）表示的360°全景的环绕拓扑和极地区域不对齐。我们提出了SHERPA，一个轻量级适配框架，结合了频率选择性圆形RoPE、圆形潜编码/解码、图像侧FFN适配器和双路径训练方案。圆形RoPE仅将接缝敏感的高频水平RoPE带替换为整数周期谐波，同时保留预训练的低频频谱。配对全景路径监督几何，而未配对风格路径使用自监督偏航一致性进行无目标风格化提示。结果，SHERPA在逼真全景域和开放域风格化提示下生成360°全景。
英文摘要：
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.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
