panocontext: a whole-room 3d context model for panoramic ... · panocontext: a whole-room 3d...
TRANSCRIPT
PanoContext: A Whole-room 3D Context Model
for Panoramic Scene Understanding
Yinda Zhang Shuran Song Ping Tan† Jianxiong Xiao
Princeton University † Simon Fraser University
Alicia Clark PanoContext October 17, 2014 1 / 11
Importance of Context in Image Processing
Alicia Clark PanoContext October 17, 2014 2 / 11
Importance of Context in Image Processing
Alicia Clark PanoContext October 17, 2014 2 / 11
Importance of Context in Image Processing
Alicia Clark PanoContext October 17, 2014 2 / 11
Importance of Context in Image Processing
Alicia Clark PanoContext October 17, 2014 2 / 11
Importance of Context in Image Processing
Context ModelsProposed in the past, but they do not work as well as expected
WHY?
Alicia Clark PanoContext October 17, 2014 2 / 11
Field of View (FOV)
Small FOV =⇒ Hinders the contextual information
Alicia Clark PanoContext October 17, 2014 3 / 11
Field of View (FOV)
Alicia Clark PanoContext October 17, 2014 3 / 11
Field of View (FOV)
Alicia Clark PanoContext October 17, 2014 3 / 11
Panorama - 360◦ Horizontal and 180◦ Vertical
Easily obtained by smartphones, special lenses, or image stitching
All objects are usually visible despite occlusion
Enables the detection of the room layout and of the contextualinformation
Panorama =⇒ Object Detection =⇒ Whole-room 3D ContextModel
Alicia Clark PanoContext October 17, 2014 4 / 11
Panorama - 360◦ Horizontal and 180◦ Vertical
Easily obtained by smartphones, special lenses, or image stitchingAll objects are usually visible despite occlusion
Enables the detection of the room layout and of the contextualinformation
Panorama =⇒ Object Detection =⇒ Whole-room 3D ContextModel
1Manhattan world assumption: assumes the scene consists of 3D cuboidsaligned with the three principle directions
2Assume no floating objectsAlicia Clark PanoContext October 17, 2014 4 / 11
PanoContext: A Whole-Room 3D Context Model
Algorithm1 Generate a set of hypotheses for room layout and objects
2 Rank these whole-room hypotheses holistically to determine thebest hypothesis
Alicia Clark PanoContext October 17, 2014 5 / 11
PanoContext: A Whole-Room 3D Context Model
1. Generate a set of whole-room hypotheses
Alicia Clark PanoContext October 17, 2014 6 / 11
PanoContext: A Whole-Room 3D Context Model
1. Generate a set of whole-room hypotheses
Figure : Hough transform for vanishing point detection
Alicia Clark PanoContext October 17, 2014 6 / 11
PanoContext: A Whole-Room 3D Context Model
1. Generate a set of whole-room hypotheses
Alicia Clark PanoContext October 17, 2014 6 / 11
PanoContext: A Whole-Room 3D Context Model
1. Generate a set of whole-room hypotheses
Figure : Comparison of OM and GC. OM works better on the top half ofthe image, while GC provides better normal estimation at the bottom
Alicia Clark PanoContext October 17, 2014 6 / 11
PanoContext: A Whole-Room 3D Context Model
1. Generate a set of whole-room hypotheses
Alicia Clark PanoContext October 17, 2014 6 / 11
PanoContext: A Whole-Room 3D Context Model
1. Generate a set of whole-room hypotheses
Alicia Clark PanoContext October 17, 2014 6 / 11
PanoContext: A Whole-Room 3D Context Model
1. Generate a set of whole-room hypotheses
Alicia Clark PanoContext October 17, 2014 6 / 11
PanoContext: A Whole-Room 3D Context Model
1. Generate a set of whole-room hypotheses
Alicia Clark PanoContext October 17, 2014 6 / 11
PanoContext: A Whole-Room 3D Context Model
1. Generate a set of whole-room hypotheses
Figure : Two ways to generate object hypotheses
Alicia Clark PanoContext October 17, 2014 6 / 11
PanoContext: A Whole-Room 3D Context Model
1. Generate a set of whole-room hypotheses
Alicia Clark PanoContext October 17, 2014 6 / 11
PanoContext: A Whole-Room 3D Context Model
1. Generate a set of whole-room hypotheses
Alicia Clark PanoContext October 17, 2014 6 / 11
PanoContext: A Whole-Room 3D Context Model
1. Generate a set of whole-room hypotheses
1Semantic LabelAlicia Clark PanoContext October 17, 2014 6 / 11
PanoContext: A Whole-Room 3D Context Model
1. Generate a set of whole-room hypotheses
Alicia Clark PanoContext October 17, 2014 6 / 11
PanoContext: A Whole-Room 3D Context Model
1. Generate a set of whole-room hypotheses
1Pairwise ConstraintAlicia Clark PanoContext October 17, 2014 6 / 11
PanoContext: A Whole-Room 3D Context Model
1. Generate a set of whole-room hypotheses
Alicia Clark PanoContext October 17, 2014 6 / 11
PanoContext: A Whole-Room 3D Context Model
2. Determine the best whole-room hypothesesTrain a linear SVM model to rank the whole-room hypothesesand choose the best hypothesis
Want the matching cost (difference between whole-roomhypothesis and its ground truth) to be as low as possible
Alicia Clark PanoContext October 17, 2014 7 / 11
Summary: How does context help?
Helps to determine the size of objects
Helps to determine the correct number of objects
Helps the determine the relative position of objects
Alicia Clark PanoContext October 17, 2014 8 / 11
Summary: How does context help?
Helps to determine the size of objects
Helps to determine the correct number of objects
Helps the determine the relative position of objects
Alicia Clark PanoContext October 17, 2014 8 / 11
Summary: How does context help?
Helps to determine the size of objects
Helps to determine the correct number of objects
Helps the determine the relative position of objects
Alicia Clark PanoContext October 17, 2014 8 / 11
Summary: How does context help?
1DPM: Deformable Part Model2Felzenszwalb et. al: Discriminative training with partially labeled data
Alicia Clark PanoContext October 17, 2014 9 / 11
Contributions
Context model is fully in 3D
First annotated panorama dataset
Alicia Clark PanoContext October 17, 2014 10 / 11
Questions?
Alicia Clark PanoContext October 17, 2014 11 / 11