发表机构
Insta360 Research; Tsinghua University; Beihang University; Wuhan University（影石创新研究院; 清华大学; 北京航空航天大学; 武汉大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
该研究提出两阶段框架Canvas360用于上下文全景生成，结合几何感知预训练与微调。通过构建数据集及特定建模方法，增强文本到全景生成，经实验验证其能提高全景图像保真度，在相关指标上表现优异。
AI 中文摘要
在这项工作中，我们提出了Canvas360，这是一个用于上下文全景生成的两阶段框架，它将几何感知预训练与下游任务特定的微调相结合。为解决缺乏针对上下文全景任务的大规模、高质量训练数据的问题，我们提出了Canvas360Dataset，它包含100万个用于风格迁移、图像修复、图像扩展和编辑的高质量配对全景样本。在建模方面，Canvas360通过并行深度生成、速度循环填充和相似性损失正则化来增强文本到全景的生成。实验表明，Canvas360提高了全景图像保真度，在全景特定的FAED指标上表现出色，并在定量评估中取得了有竞争力或领先的结果。
英文摘要
In this work, we present Canvas360, a two-stage framework for in-context panoramic generation that combines geometry-aware pretraining with downstream task-specific fine-tuning. To address the lack of large-scale, high-quality training data tailored to in-context panoramic tasks, we propose Canvas360Dataset, a collection of 1M high-quality paired panoramic samples for style transfer, inpainting, outpainting, and editing, enabling effective supervision across diverse in-context generation scenarios. On the modeling side, Canvas360 enhances text-to-panorama generation through parallel depth generation, velocity circular padding, and similarity loss regularization, enabling the model to learn geometry-aware representations, capture object distortion details, and improve geometric consistency and global coherence. Furthermore, empowered by strong panoramic priors, Canvas360 enables a unified in-context panoramic generation framework that supports diverse downstream tasks via token-level concatenation, surpassing prior methods in both task coverage and modeling flexibility. Extensive experiments show that Canvas360 improves panoramic image fidelity, achieving particularly strong performance on the panorama-specific FAED metric and competitive or leading results across the reported quantitative evaluations. More information can be found on our project page: https://zry000.github.io/Canvas360/
CommentsProject page: https://zry000.github.io/Canvas360/ Github: https://github.com/Insta360-Research-Team/Canvas360
