SE360: Semantic Edit in 360° Panoramas via Hierarchical Data Construction
Proceedings of the AAAI Conference on Artificial Intelligence · 14.03.2026 · 40 (16) · 13512-13520
DOI: 10.1609/aaai.v40i16.38356 ↗Kurz gefasst
Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 14.03.2026. Verfasst von Haoyi Zhong und 3 weiteren Autor:innen.
Abstract (Originalsprache)
While instruction-based image editing is emerging, extending it to 360° panorama introduces additional challenges. Existing methods often produce implausible results in both equirectangular projections (ERP) and perspective views. To address these limitations, we propose SE360, a novel framework for multi-condition guided object editing in 360° panoramas. At its core is a novel coarse-to-fine autonomous data generation pipeline without manual intervention. This pipeline leverages a Vision-Language Model (VLM) and adaptive projection adjustment for hierarchical analysis, ensuring the holistic segmentation of objects and their physical context. The resulting data pairs are both semantically meaningful and geometrically consistent, even when sourced from unlabeled panoramas. Furthermore, we introduce a cost-effective, two-stage data refinement strategy to improve data realism and mitigate model overfitting to erasing artifacts. Based on the constructed dataset, we train a Transformer-based diffusion model to allow flexible object editing guided by text, mask, or reference image in 360° panoramas. Our experiments demonstrate that our method outperforms existing methods in both visual quality and semantic accuracy.
Zitieren
APA
Zhong, H., Zhang, F., Chalmers, A., & Rhee, T. (2026). SE360: Semantic Edit in 360° Panoramas via Hierarchical Data Construction. Proceedings of the AAAI Conference on Artificial Intelligence, 40(16), 13512-13520. https://doi.org/10.1609/aaai.v40i16.38356
Vancouver
Zhong H, Zhang F, Chalmers A, Rhee T. SE360: Semantic Edit in 360° Panoramas via Hierarchical Data Construction. Proceedings of the AAAI Conference on Artificial Intelligence. 2026;40(16):13512-13520. doi:10.1609/aaai.v40i16.38356
BibTeX
@article{Zhong2026,
author = {Zhong, Haoyi and Zhang, Fang-Lue and Chalmers, Andrew and Rhee, Taehyun},
title = {SE360: Semantic Edit in 360° Panoramas via Hierarchical Data Construction},
journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
year = {2026},
volume = {40},
number = {16},
pages = {13512--13520},
doi = {10.1609/aaai.v40i16.38356}
}
EUVIMED