Enhancing In-context Panoramic Generation via Geometric-aware Pretraining
2026-07-09 • Computer Vision and Pattern Recognition
Computer Vision and Pattern Recognition
AI summaryⓘ
The authors introduce Canvas360, a two-step approach to create panoramic images that understand 3D shapes better by first training on a specialized large dataset and then fine-tuning for specific tasks like editing or style transfer. They created a big dataset called Canvas360Dataset with one million panoramic images to help teach the model various image editing skills. Their method improves how the model handles depth and object shapes in panoramas, making the final images more realistic and consistent. Canvas360 works for many different panorama tasks in one system and outperforms previous methods in quality and versatility.
panoramic generationgeometry-aware pretrainingstyle transferinpaintingoutpaintingfine-tuningdepth generationsimilarity lossimage fidelityFAED metric
Authors
Haoran Feng, Ruiyang Zhang, Longyi Zhang, Dizhe Zhang, Lu Qi
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/