Search-and-replace editing for personal photo collections

By Samuel W. Hasinoff, M. Jóźwiak, Frédo Durand, William T. Freeman. 2010

18 citations recorded by the source corpus.

We propose a new system for editing personal photo collections, inspired by search-and-replace editing for text. In our system, local edits specified by the user in a single photo (e.g., using the “clone brush” tool) can be propagated automatically to other photos in the same collection, by matching the edited region across photos. To achieve this, we build on tools from computer vision for image matching. Our experimental results on real photo collections demonstrate the feasibility and potential benefits of our approach.

Subfields: Computer Vision and Pattern Recognition, Human-Computer Interaction

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

In Human-Computer Interaction

Citations in the corpus

Rewriting a Deep Generative Model (2020, background): “Edit transfer methods propagate pixel edits to corresponding locations in other images of the same object or adjacent frames in the same video [2,77,28,14,13,81,21].”
Transfusive image manipulation (2012, methodology): “Another possibility would be to use the warps of previous works such as [Hasinoff et al. 2010; HaCohen et al. 2011] as initialization for ours.”
Light Field Image Processing: An Overview (2017, background): “tured light fields [217], [218], video [209], [219]–[221] or image collections [222]–[224].”
FlowWeb: Joint image set alignment by weaving consistent, pixel-wise correspondences (2015, background): “But going from coarse to fine-grained pixel-wise correspondence is still very much an open problem, the solution to which could benefit many vision and graphics tasks, including image edit propagation [14, 46], co-segmentation [34, 7], structurefrom-motion [36], 3D object reconstruction [4, 39] unsu”
Editing Conditional Radiance Fields (2021, background): “A closely related concept is edit propagation [3, 19, 23, 74, 77], which propagates sparse user edits on a single image to an entire photo collection or video.”