SphereDrag: Spherical Geometry-Aware Panoramic Image Editing

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Feng, Zhiao, Li, Xuewei, Yang, Junjie, Li, Jingchao, Peng, Yuxin, Li, Xi
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866911212971753472
author Feng, Zhiao
Li, Xuewei
Yang, Junjie
Li, Jingchao
Peng, Yuxin
Li, Xi
author_facet Feng, Zhiao
Li, Xuewei
Yang, Junjie
Li, Jingchao
Peng, Yuxin
Li, Xi
contents Image editing has made great progress on planar images, but panoramic image editing remains underexplored. Due to their spherical geometry and projection distortions, panoramic images present three key challenges: boundary discontinuity, trajectory deformation, and uneven pixel density. To tackle these issues, we propose SphereDrag, a novel panoramic editing framework utilizing spherical geometry knowledge for accurate and controllable editing. Specifically, adaptive reprojection (AR) uses adaptive spherical rotation to deal with discontinuity; great-circle trajectory adjustment (GCTA) tracks the movement trajectory more accurate; spherical search region tracking (SSRT) adaptively scales the search range based on spherical location to address uneven pixel density. Also, we construct PanoBench, a panoramic editing benchmark, including complex editing tasks involving multiple objects and diverse styles, which provides a standardized evaluation framework. Experiments show that SphereDrag gains a considerable improvement compared with existing methods in geometric consistency and image quality, achieving up to 10.5% relative improvement.
format Preprint
id arxiv_https___arxiv_org_abs_2506_11863
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle SphereDrag: Spherical Geometry-Aware Panoramic Image Editing
Feng, Zhiao
Li, Xuewei
Yang, Junjie
Li, Jingchao
Peng, Yuxin
Li, Xi
Computer Vision and Pattern Recognition
Image editing has made great progress on planar images, but panoramic image editing remains underexplored. Due to their spherical geometry and projection distortions, panoramic images present three key challenges: boundary discontinuity, trajectory deformation, and uneven pixel density. To tackle these issues, we propose SphereDrag, a novel panoramic editing framework utilizing spherical geometry knowledge for accurate and controllable editing. Specifically, adaptive reprojection (AR) uses adaptive spherical rotation to deal with discontinuity; great-circle trajectory adjustment (GCTA) tracks the movement trajectory more accurate; spherical search region tracking (SSRT) adaptively scales the search range based on spherical location to address uneven pixel density. Also, we construct PanoBench, a panoramic editing benchmark, including complex editing tasks involving multiple objects and diverse styles, which provides a standardized evaluation framework. Experiments show that SphereDrag gains a considerable improvement compared with existing methods in geometric consistency and image quality, achieving up to 10.5% relative improvement.
title SphereDrag: Spherical Geometry-Aware Panoramic Image Editing
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2506.11863