Semantic Scholar Open Access 2015 247 sitasi

A computational approach for obstruction-free photography

Tianfan Xue Michael Rubinstein Ce Liu W. Freeman

Lihat Sumber DOI

Abstrak

We present a unified computational approach for taking photos through reflecting or occluding elements such as windows and fences. Rather than capturing a single image, we instruct the user to take a short image sequence while slightly moving the camera. Differences that often exist in the relative position of the background and the obstructing elements from the camera allow us to separate them based on their motions, and to recover the desired background scene as if the visual obstructions were not there. We show results on controlled experiments and many real and practical scenarios, including shooting through reflections, fences, and raindrop-covered windows.

Topik & Kata Kunci

Computer Science

Penulis (4)

Tianfan Xue

Michael Rubinstein

Ce Liu

W. Freeman

Format Sitasi

APA MLA BibTeX

Xue, T., Rubinstein, M., Liu, C., Freeman, W. (2015). A computational approach for obstruction-free photography. https://doi.org/10.1145/2766940

Akses Cepat

Lihat di Sumber doi.org/10.1145/2766940

Informasi Jurnal

Tahun Terbit: 2015
Bahasa: en
Total Sitasi: 247×
Sumber Database: Semantic Scholar
DOI: 10.1145/2766940
Akses: Open Access ✓