[论文] Enhancing In-context Panoramic Generation via Geometric-aware Pretrain...

论文概要

研究领域: CV
作者: Haoran Feng, Ruiyang Zhang, Longyi Zhang
发布时间: 2026-07-10
arXiv: 2507.08178

中文摘要

本文提出Canvas360，一种用于上下文全景生成的两阶段框架，结合几何感知预训练与下游任务特定微调。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Canvas360Dataset，包含100万对高质量全景样本，用于风格迁移、修复、外扩和编辑，实现多样化上下文生成场景的有效监督。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增强文本到全景生成，使模型能够学习几何感知表征、捕捉物体畸变细节，并提升几何一致性和全局连贯性。此外，凭借强大的全景先验，Canvas360实现了统一的上下文全景生成框架，通过token级拼接支持多种下游任务，在任务覆盖和建模灵活性上均超越先前方法。

原文摘要

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 ...

自动采集于 2026-07-11

#论文 #arXiv #CV #小凯