Inverse Image Editing:
Recovering a Semantic Editing History from a Before-and-After Image Pair

Shi-Min Hu1, Kun Xu1, Li-Qian Ma1, Bin Liu1, Bi-Ye Jiang1, Jue Wang2
1Tsinghua University
2Adobe Research




Abstract: We study the problem of inverse image editing, which recovers a semantically-meaningful editing history from a source image and an edited copy. Our approach supports a wide range of commonly-used editing operations such as cropping, object insertion and removal, linear and non-linear color transformations, and spatially-varying adjustment brushes. Given an input image pair, we first apply a dense correspondence method between them to match edited image regions with their sources. For each edited region, we determine geometric and semantic appearance operations that have been applied. Finally, we compute an optimal editing path from the region-level editing operations, based on predefined semantic constraints. The recovered history can be used in various applications such as image re-editing, edit transfer, and image revision control. A user study suggests that the editing histories generated from our system are semantically comparable to the ones generated by artists.

Paper: [PDF 8.2M].
Presentation: [PPTX 43.4M]
Supplemental Document: [PDF 13.6M].
Bibtex: @article{Hu13InverseImageEditing,
author = {Shi-Min Hu and Kun Xu and Li-Qian Ma and Bin Liu and Bi-Ye Jiang and Jue Wang},
title = {Inverse Image Editing: Recovering a Semantic Editing History from a Before-and-After Image Pair},
journal = {ACM Transactions on Graphics},
volume = {32},
number = {6},
year = {2013},
pages = {194:1--194:11},
}