| title | Enhancing In-context Panoramic Generation via Geometric-aware Pretraining |
|---|---|
| authors | Haoran Feng, Ruiyang Zhang, Longyi Zhang, Dizhe Zhang, Lu Qi |
| date | 2026-07-09 |
| venue | arXiv (preprint, not peer reviewed) |
| id | arXiv:2607.08765 |
| affiliation | Insta360 |
| upvotes | 21 (Hugging Face Daily Papers, 2026-11-01) |
| links | abs pdf hf code |
| abstract | 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/ |
cite
@misc{feng2026enhancing,
title={Enhancing In-context Panoramic Generation via Geometric-aware Pretraining},
author={Haoran Feng and Ruiyang Zhang and Longyi Zhang and Dizhe Zhang and Lu Qi},
year={2026},
eprint={2607.08765},
archivePrefix={arXiv},
url={https://arxiv.org/abs/2607.08765}
}