Limits...
Basic level scene understanding: categories, attributes and structures.

Xiao J, Hays J, Russell BC, Patterson G, Ehinger KA, Torralba A, Oliva A - Front Psychol (2013)

Bottom Line: This database allows us to systematically study the space of scenes and to establish a benchmark for scene and object recognition.We augment the categorical SUN database with 102 scene attributes for every image and explore attribute recognition.Finally, we present an integrated system to extract the 3D structure of the scene and objects depicted in an image.

View Article: PubMed Central - PubMed

Affiliation: Computer Science, Princeton University Princeton, NJ, USA.

ABSTRACT
A longstanding goal of computer vision is to build a system that can automatically understand a 3D scene from a single image. This requires extracting semantic concepts and 3D information from 2D images which can depict an enormous variety of environments that comprise our visual world. This paper summarizes our recent efforts toward these goals. First, we describe the richly annotated SUN database which is a collection of annotated images spanning 908 different scene categories with object, attribute, and geometric labels for many scenes. This database allows us to systematically study the space of scenes and to establish a benchmark for scene and object recognition. We augment the categorical SUN database with 102 scene attributes for every image and explore attribute recognition. Finally, we present an integrated system to extract the 3D structure of the scene and objects depicted in an image.

No MeSH data available.


Random subset of hypotheses generated for one image, ordered increasingly by their values of loss function △(yn, ŷ).
© Copyright Policy - open-access
Related In: Results  -  Collection

License
getmorefigures.php?uid=PMC3756302&req=5

Figure 12: Random subset of hypotheses generated for one image, ordered increasingly by their values of loss function △(yn, ŷ).

Mentions: We propose a two step algorithm for generating hypotheses and performing fast inference. For any image, either during training or testing, we first generate a large pool of initial hypotheses, without considering the objective function. Then, we do several iterations of heuristic search, based on the initial hypothesis pool and w, and simply pick the one with the highest objective value wTf as the solution. Figure 12 shows some examples of hypotheses generated.


Basic level scene understanding: categories, attributes and structures.

Xiao J, Hays J, Russell BC, Patterson G, Ehinger KA, Torralba A, Oliva A - Front Psychol (2013)

Random subset of hypotheses generated for one image, ordered increasingly by their values of loss function △(yn, ŷ).
© Copyright Policy - open-access
Related In: Results  -  Collection

License
Show All Figures
getmorefigures.php?uid=PMC3756302&req=5

Figure 12: Random subset of hypotheses generated for one image, ordered increasingly by their values of loss function △(yn, ŷ).
Mentions: We propose a two step algorithm for generating hypotheses and performing fast inference. For any image, either during training or testing, we first generate a large pool of initial hypotheses, without considering the objective function. Then, we do several iterations of heuristic search, based on the initial hypothesis pool and w, and simply pick the one with the highest objective value wTf as the solution. Figure 12 shows some examples of hypotheses generated.

Bottom Line: This database allows us to systematically study the space of scenes and to establish a benchmark for scene and object recognition.We augment the categorical SUN database with 102 scene attributes for every image and explore attribute recognition.Finally, we present an integrated system to extract the 3D structure of the scene and objects depicted in an image.

View Article: PubMed Central - PubMed

Affiliation: Computer Science, Princeton University Princeton, NJ, USA.

ABSTRACT
A longstanding goal of computer vision is to build a system that can automatically understand a 3D scene from a single image. This requires extracting semantic concepts and 3D information from 2D images which can depict an enormous variety of environments that comprise our visual world. This paper summarizes our recent efforts toward these goals. First, we describe the richly annotated SUN database which is a collection of annotated images spanning 908 different scene categories with object, attribute, and geometric labels for many scenes. This database allows us to systematically study the space of scenes and to establish a benchmark for scene and object recognition. We augment the categorical SUN database with 102 scene attributes for every image and explore attribute recognition. Finally, we present an integrated system to extract the 3D structure of the scene and objects depicted in an image.

No MeSH data available.