Share This Author
Learning to predict where humans look
- Tilke Judd, Krista A. Ehinger, F. Durand, A. Torralba
- Computer ScienceIEEE 12th International Conference on Computer…
- 1 September 2009
This paper collects eye tracking data of 15 viewers on 1003 images and uses this database as training and testing examples to learn a model of saliency based on low, middle and high-level image features.
Fast bilateral filtering for the display of high-dynamic-range images
We present a new technique for the display of high-dynamic-range images, which reduces the contrast while preserving detail. It is based on a two-scale decomposition of the image into a base layer,...
Eulerian video magnification for revealing subtle changes in the world
- Hao-Yu Wu, Michael Rubinstein, Eugene Shih, J. Guttag, F. Durand, W. Freeman
- Computer ScienceACM Trans. Graph.
- 1 July 2012
Using the Eulerian Video Magnification method, the flow of blood as it fills the face is able to be visualize and the resulting signal is amplified to reveal hidden information.
Halide: a language and compiler for optimizing parallelism, locality, and recomputation in image processing pipelines
- Jonathan Ragan-Kelley, Connelly Barnes, Andrew Adams, Sylvain Paris, F. Durand, Saman P. Amarasinghe
- Computer SciencePLDI
- 16 June 2013
A systematic model of the tradeoff space fundamental to stencil pipelines is presented, a schedule representation which describes concrete points in this space for each stage in an image processing pipeline, and an optimizing compiler for the Halide image processing language that synthesizes high performance implementations from a Halide algorithm and a schedule are presented.
Understanding and evaluating blind deconvolution algorithms
- Anat Levin, Yair Weiss, F. Durand, W. Freeman
- Computer ScienceIEEE Conference on Computer Vision and Pattern…
- 20 June 2009
The previously reported failure of the naive MAP approach is explained by demonstrating that it mostly favors no-blur explanations and it is shown that since the kernel size is often smaller than the image size a MAP estimation of the kernel alone can be well constrained and accurately recover the true blur.
Efficient marginal likelihood optimization in blind deconvolution
This paper derives a simple approximated MAPk algorithm which involves only a modest modification of common MAPx, k algorithms, and shows that MAPk can, in fact, be optimized easily, with no additional computational complexity.
Learning photographic global tonal adjustment with a database of input/output image pairs
This work creates a high-quality reference dataset, collects 5,000 photos, manually annotated them, and hired 5 trained photographers to retouch each picture, and introduces difference learning: this method models and predicts difference between users.
Image and depth from a conventional camera with a coded aperture
A simple modification to a conventional camera is proposed to insert a patterned occluder within the aperture of the camera lens, creating a coded aperture, and introduces a criterion for depth discriminability which is used to design the preferred aperture pattern.
A Benchmark of Computational Models of Saliency to Predict Human Fixations
A benchmark data set containing 300 natural images with eye tracking data from 39 observers is proposed to compare model performances and it is shown that human performance increases with the number of humans to a limit.
Phase-based video motion processing
A technique to manipulate small movements in videos based on an analysis of motion in complex-valued image pyramids that supports larger amplification factors and is significantly less sensitive to noise is introduced.