Differences

This shows you the differences between two versions of the page.

publications:crisp-boundaries [2014/07/24 15:12]
phillip created
publications:crisp-boundaries [2017/09/15 12:34] (current)
elmer
Line 1: Line 1:
-====== Looking against the light: How perception of translucency depends on lighting direction ====== +====== Crisp Boundary Detection Using Pointwise Mutual Information ====== 
-==== Xiao, B., Walter. B., Gkioulekas, I., Zickler, T., Adelson. E. H., Bala, K. ====+==== Isola, P., Zoran, D., Krishnan, D., Adelson. E. H. ====
---- ----
===== Abstract ===== ===== Abstract =====
-Translucency is an important aspect of material appearance. To some extent, humans are able to estimate translucency in a consistent way across different shapes and lighting conditions, i.e., to exhibit translucency constancy. However, Fleming and Bülthoff (2005) have shown that that there can be large failures of constancy, with lighting direction playing an important role. In this paper, we explore the interaction of shape, illumination, and degree of translucency constancy more deeply by including in our analysis the variations in translucent appearance that are induced by the shape of the scattering phase function. This is an aspect of translucency that has been largely neglected. We used appearance matching to measure how perceived translucency depends on both lighting and phase function. The stimuli were rendered scenes that contained a figurine and the lighting direction was represented by spherical harmonic basis function. Observers adjusted the density of a figurine under one lighting condition to match the material property of a target figurine under another lighting condition. Across the trials, we varied both the lighting direction and the phase function of the target. The phase functions were sampled from a 2D space proposed by Gkioulekas et al. (2013) to span an important range of translucent appearance. We find the degree of translucency constancy depends strongly on the phase function's location in the same 2D space, suggesting that the space captures useful information about different types of translucency. We also find that the geometry of an object is important. We compare the case of a torus, which has a simple smooth shape, with that of the figurine, which has more complex geometric features. The complex shape shows a greater range of apparent translucencies and a higher degree of constancy failure. In summary, humans show significant failures of translucency constancy across changes in lighting direction, but the effect depends both on the shape complexity and the translucency phase function.+Detecting boundaries between semantically meaningful objects in visual scenes is an important component of many vision algorithms. In this paper, we propose a novel method for detecting such boundaries based on a simple underlying principle: pixels belonging to the same object exhibit higher statistical dependencies than pixels belonging to different objects. We show how to derive an affinity measure based on this principle using pointwise mutual information, and we show that this measure is indeed a good predictor of whether or not two pixels reside on the same object. Using this affinity with spectral clustering, we can find object boundaries in the image -- achieving state-of-the-art results on the BSDS500 dataset. Our method produces pixel-level accurate boundaries while requiring minimal feature engineering.
 +
 +===== Project page =====
 +[[http://web.mit.edu/phillipi/crisp_boundaries | Crisp Boundary Detection Using Pointwise Mutual Information ]]
===== Information ===== ===== Information =====
Line 15: Line 18:
shortcite    : ECCV shortcite    : ECCV
year         : 2014 year         : 2014
 +created_dt   : 2014-01-01
summary_page : publications:crisp-boundaries summary_page : publications:crisp-boundaries
keyword_tags : isola, adelson keyword_tags : isola, adelson
-www_url      : http://web.mit.edu/phillipi/crisp_boundaries 
pdf_url      : http://web.mit.edu/phillipi/www/publications/crisp_boundaries.pdf pdf_url      : http://web.mit.edu/phillipi/www/publications/crisp_boundaries.pdf
type         : publication type         : publication
 
publications/crisp-boundaries.1406229129.txt.gz · Last modified: 2014/07/24 15:12 by phillip