Abstract:
Images are static and lack important depth information of underlying 3D scenes. We introduce interactive images in the context of man-made environments wherein objects are simple, regular, share various non-local relations (e.g., coplanarity, repetitions, etc.), and are often repeated. We present an interactive framework to create a partial scene reconstruction based on cuboid-proxies using minimal user interaction. This enables a range of intuitive image edits mimicking real-world behavior, which are otherwise difficult to achieve. Effectively, the user simply provides high-level semantic hints, while our system ensures plausible operations by conforming to the extracted non-local relations. We demonstrate our system on a range of real-world images and validate the plausibility of the results using a user study.
System Pipeline:
![]() |
Results:
![]() |
Video:
Acknowledgements:
Bibtex:
@article{zcczhm_interactiveImages_sigg12,
AUTHOR = "Youyi Zheng and Xiang Chen and Ming-Ming Cheng and Kun Zhou and Shi-Min Hu and Niloy J. Mitra",
TITLE = "Interactive Images: Cuboid Proxies for Smart Image Manipulation",
JOURNAL = "ACM Transactions on Graphics",
VOLUME = "31",
NUMBER = "4",
YEAR = "2012",
pages = {99:1--99:11},
articleno = {99},
numpages = {11},
}
|
|