2007
DOI: 10.1007/s11263-006-0031-y
|View full text |Cite
|
Sign up to set email alerts
|

Recovering Surface Layout from an Image

Abstract: Humans have an amazing ability to instantly grasp the overall 3D structure of a scene-ground orientation, relative positions of major landmarks, etc.-even from a single image. This ability is completely missing in most popular recognition algorithms, which pretend that the world is flat and/or view it through a patch-sized peephole. Yet it seems very likely that having a grasp of this "surface layout" of a scene should be of great assistance for many tasks, including recognition, navigation, and novel view syn… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
3
1
1

Citation Types

4
591
0
4

Year Published

2011
2011
2020
2020

Publication Types

Select...
8

Relationship

0
8

Authors

Journals

citations
Cited by 595 publications
(599 citation statements)
references
References 42 publications
4
591
0
4
Order By: Relevance
“…Practically none of the ground pixels are mislabeled as sky. These numbers agree quite well with the confusion matrix in [24].…”
Section: Sky/ground Discriminationsupporting
confidence: 87%
See 2 more Smart Citations
“…Practically none of the ground pixels are mislabeled as sky. These numbers agree quite well with the confusion matrix in [24].…”
Section: Sky/ground Discriminationsupporting
confidence: 87%
“…It is thus desirable to differentiate the two based on region characteristics such as color. There are many options here, but we chose to use the surface layout classifier of [8,24]. This method divides images into geometric classes corresponding to three kinds of surfaces: support (aka ground), vertical, or sky.…”
Section: Sky/ground Discriminationmentioning
confidence: 99%
See 1 more Smart Citation
“…We choose the superpixels obtained by color based over segmentation scheme proposed in [24]. The choice of features has been adopted from [25] where each superpixel is characterized by location and shape (position of the centroid, relative position, number of pixels and area in the image), color (color histograms of RGB, HSV values and saturation value), texture (mean absolute response of the filter bank of 15 filters and histogram of maximum responses) and perspective cues computed from long linear segments and lines aligned with different vanishing points. The entire feature vector is of 194 dimensions.…”
Section: Unary Termmentioning
confidence: 99%
“…A more commonly used strategy is to integrate the results over multiple di erent segmentations of the same scene [6,18,13,19]. Usually several unsupervised bottom-up segmentation algorithms, each with di erent parameters are used.…”
Section: Introductionmentioning
confidence: 99%