Dragging with Geometry: From Pixels to Geometry-Guided Image Editing
This addresses the need for more accurate and coherent image editing tools for users in computer vision and graphics, though it is incremental as it builds on existing drag-based methods by incorporating 3D cues.
The paper tackled the problem of imprecise and inconsistent edits in interactive point-based image editing, particularly for geometry-intensive scenarios like rotations and perspective transformations, by proposing GeoDrag, a geometry-guided method that achieved superior precision, structural consistency, and reliable multi-point editability in experiments.
Interactive point-based image editing serves as a controllable editor, enabling precise and flexible manipulation of image content. However, most drag-based methods operate primarily on the 2D pixel plane with limited use of 3D cues. As a result, they often produce imprecise and inconsistent edits, particularly in geometry-intensive scenarios such as rotations and perspective transformations. To address these limitations, we propose a novel geometry-guided drag-based image editing method - GeoDrag, which addresses three key challenges: 1) incorporating 3D geometric cues into pixel-level editing, 2) mitigating discontinuities caused by geometry-only guidance, and 3) resolving conflicts arising from multi-point dragging. Built upon a unified displacement field that jointly encodes 3D geometry and 2D spatial priors, GeoDrag enables coherent, high-fidelity, and structure-consistent editing in a single forward pass. In addition, a conflict-free partitioning strategy is introduced to isolate editing regions, effectively preventing interference and ensuring consistency. Extensive experiments across various editing scenarios validate the effectiveness of our method, showing superior precision, structural consistency, and reliable multi-point editability. The code will be available on https://github.com/xinyu-pu/GeoDrag .