EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

AnyStitch: Generative Large Parallax Image Stitching

Zixuan Chen, Lingen Li, Junhao Zhuang, Ruikang Li, Tianfan Xue

ACM Transactions on Graphics · 09.11.2026 · 45 (6) · 1-13

DOI: 10.1145/3842587 ↗

Kurz gefasst

Fachartikel in der Zeitschrift ACM Transactions on Graphics, online erschienen am 09.11.2026. Verfasst von Zixuan Chen und 4 weiteren Autor:innen. Die Arbeit nennt 47 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Key R&D Program of China, RGC Early Career Scheme.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Wide field-of-view panorama stitching is important for computational photography and immersive visual applications, but often faces some challenges like severe geometric disparities. The typical "warp-and-blend" stitching technique only works with limited parallax and fails on large-parallax scenes, due to its inherent restriction to 2D geometric transformations that cannot resolve underlying 3D structures. To break this limitation, we present AnyStitch, a generative framework that can merge multiple reference images with large parallax into a seamless panorama. Unlike previous methods, we formulate the stitching problem as a reference-based image generation process, which naturally avoids stitching artifacts. Specifically, we propose a Hierarchical Projected Rotary Positional Encoding (HPRoPE) based on a 3D feed-forward model to establish accurate geometric relationships between the inputs and the panoramic canvas while preserving fidelity. Given that the resolution of the generated image varies with the number of inputs, we design a spatial autoregressive generation strategy to generate visually coherent panoramas at flexible resolutions. Finally, to enable the supervised fine-tuning of the proposed model, we construct a paired dataset utilizing 3D Gaussian Splatting (3DGS) scenes. Experiments demonstrate that AnyStitch can seamlessly stitch a variable number of inputs (like 22 views in teaser) with large camera motion, support flexible control of target view and projection type, and handle simple dynamic scenes. Project page: https://cecret3350.github.io/AnyStitch/.

Förderung

  • National Key R&D Program of China
  • RGC Early Career Scheme

Zitieren

APA

Chen, Z., Li, L., Zhuang, J., Li, R., & Xue, T. (2026). AnyStitch: Generative Large Parallax Image Stitching. ACM Transactions on Graphics, 45(6), 1-13. https://doi.org/10.1145/3842587

Vancouver

Chen Z, Li L, Zhuang J, Li R, Xue T. AnyStitch: Generative Large Parallax Image Stitching. ACM Transactions on Graphics. 2026;45(6):1-13. doi:10.1145/3842587

BibTeX
@article{Chen2026,
  author = {Chen, Zixuan and Li, Lingen and Zhuang, Junhao and Li, Ruikang and Xue, Tianfan},
  title = {AnyStitch: Generative Large Parallax Image Stitching},
  journal = {ACM Transactions on Graphics},
  year = {2026},
  volume = {45},
  number = {6},
  pages = {1--13},
  doi = {10.1145/3842587}
}
Kostenlos starten →