ML Anthology

Why I Want a Gradient Camera

Jack Tumblin, Amit K. Agrawal, Ramesh Raskar
CVPR 2005 pp. 103-110
doi:10.1109/CVPR.2005.374 /cvpr/2005/tumblin2005cvpr-i/

Abstract

We propose a camera that measures static gradients instead of static intensities. Quantizing sensed intensity differences between adjacent pixel values permits an ordinary A/D converter to measure detailed high contrast (HDR) scenes. We measure alternating `cliques' of sensors (small groups) that locally determine their own best exposure, and reconstruct the image using a Poisson solver. This intrinsically differential design suppresses common-mode noise, hides and smoothes quantization, and can correct for its own saturated sensors. Simulations demonstrate these capabilities in side-by-side comparisons.

PDF CVPR Semantic Scholar

Cite

Text

Tumblin et al. "Why I Want a Gradient Camera." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2005. doi:10.1109/CVPR.2005.374

Markdown

[Tumblin et al. "Why I Want a Gradient Camera." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2005.](https://mlanthology.org/cvpr/2005/tumblin2005cvpr-i/) doi:10.1109/CVPR.2005.374

BibTeX

@inproceedings{tumblin2005cvpr-i,
  title     = {{Why I Want a Gradient Camera}},
  author    = {Tumblin, Jack and Agrawal, Amit K. and Raskar, Ramesh},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  year      = {2005},
  pages     = {103-110},
  doi       = {10.1109/CVPR.2005.374},
  url       = {https://mlanthology.org/cvpr/2005/tumblin2005cvpr-i/}
}