ee290t : 3d reconstruction and recognition
TRANSCRIPT
![Page 1: EE290T : 3D Reconstruction and Recognition](https://reader031.vdocuments.us/reader031/viewer/2022012506/61823f53e60c1062c67d4366/html5/thumbnails/1.jpg)
EE290T : 3D Reconstruction and
Recognition
![Page 2: EE290T : 3D Reconstruction and Recognition](https://reader031.vdocuments.us/reader031/viewer/2022012506/61823f53e60c1062c67d4366/html5/thumbnails/2.jpg)
Acknowledgement
Courtesy of Prof. Silvio Savarese.
![Page 3: EE290T : 3D Reconstruction and Recognition](https://reader031.vdocuments.us/reader031/viewer/2022012506/61823f53e60c1062c67d4366/html5/thumbnails/3.jpg)
Introduction
![Page 4: EE290T : 3D Reconstruction and Recognition](https://reader031.vdocuments.us/reader031/viewer/2022012506/61823f53e60c1062c67d4366/html5/thumbnails/4.jpg)
“There was a table set out under
a tree in front of the house,and the March Hare and the
Hatter were having tea at it.”
“The table was a large one, but
the three were all crowded
together at one corner of it …”
From “A M a d Tea-Party”Alice's Adventures in W onderla n
by
Lew is Ca rroll
![Page 5: EE290T : 3D Reconstruction and Recognition](https://reader031.vdocuments.us/reader031/viewer/2022012506/61823f53e60c1062c67d4366/html5/thumbnails/5.jpg)
Illustra tion by Arthur Ra ckha m
a tree in front of the house,
and the March Hare and the
Hatter were having tea at it.”
“The table was a large one, but
the three were all crowded
together at one corner of it …”
From “A M a d Tea-Party”Alice's Adventures in W onderla n
by
Lew is Ca rroll
“There was a table set out under
![Page 6: EE290T : 3D Reconstruction and Recognition](https://reader031.vdocuments.us/reader031/viewer/2022012506/61823f53e60c1062c67d4366/html5/thumbnails/6.jpg)
-semantic
Image/ video
Computer vision
…
Object 1 Object N
- semantic
![Page 7: EE290T : 3D Reconstruction and Recognition](https://reader031.vdocuments.us/reader031/viewer/2022012506/61823f53e60c1062c67d4366/html5/thumbnails/7.jpg)
-semantic
Image/ video
…
Object 1 Object N
- semantic
-geometry -geometry
Computer vision
![Page 8: EE290T : 3D Reconstruction and Recognition](https://reader031.vdocuments.us/reader031/viewer/2022012506/61823f53e60c1062c67d4366/html5/thumbnails/8.jpg)
-semantic
Image/ video
…
Object 1 Object N
- semantic
-geometry -geometry
spatial & temporal relations
Computer vision
![Page 9: EE290T : 3D Reconstruction and Recognition](https://reader031.vdocuments.us/reader031/viewer/2022012506/61823f53e60c1062c67d4366/html5/thumbnails/9.jpg)
-semantic
Image/ video
…
Object 1 Object N
- semantic
-geometry -geometry
spatial & temporal relations
Scene
-Sema ntic
- geometry
Computer vision
![Page 10: EE290T : 3D Reconstruction and Recognition](https://reader031.vdocuments.us/reader031/viewer/2022012506/61823f53e60c1062c67d4366/html5/thumbnails/10.jpg)
Sensing device
• Information extraction
• Interpretation
Computer vision
1. Information extraction: features, 3D structure, motion flows, etc…
2. Interpretation: recognize objects, scenes, actions, events
Computational device
![Page 11: EE290T : 3D Reconstruction and Recognition](https://reader031.vdocuments.us/reader031/viewer/2022012506/61823f53e60c1062c67d4366/html5/thumbnails/11.jpg)
Computer vision and Applications
21
1990 20102000
EosSystems
![Page 12: EE290T : 3D Reconstruction and Recognition](https://reader031.vdocuments.us/reader031/viewer/2022012506/61823f53e60c1062c67d4366/html5/thumbnails/12.jpg)
Fingerprint biometrics
![Page 13: EE290T : 3D Reconstruction and Recognition](https://reader031.vdocuments.us/reader031/viewer/2022012506/61823f53e60c1062c67d4366/html5/thumbnails/13.jpg)
Augmentation with 3D computer graphics
23
![Page 14: EE290T : 3D Reconstruction and Recognition](https://reader031.vdocuments.us/reader031/viewer/2022012506/61823f53e60c1062c67d4366/html5/thumbnails/14.jpg)
3D object prototyping
24PhotomodelerEosSystems
![Page 15: EE290T : 3D Reconstruction and Recognition](https://reader031.vdocuments.us/reader031/viewer/2022012506/61823f53e60c1062c67d4366/html5/thumbnails/15.jpg)
Computer vision and Applications
25
1990 20102000
EosSystems Autostich
![Page 16: EE290T : 3D Reconstruction and Recognition](https://reader031.vdocuments.us/reader031/viewer/2022012506/61823f53e60c1062c67d4366/html5/thumbnails/16.jpg)
Face detection
![Page 17: EE290T : 3D Reconstruction and Recognition](https://reader031.vdocuments.us/reader031/viewer/2022012506/61823f53e60c1062c67d4366/html5/thumbnails/17.jpg)
Face detection
![Page 18: EE290T : 3D Reconstruction and Recognition](https://reader031.vdocuments.us/reader031/viewer/2022012506/61823f53e60c1062c67d4366/html5/thumbnails/18.jpg)
Web applications
28Photometria
![Page 19: EE290T : 3D Reconstruction and Recognition](https://reader031.vdocuments.us/reader031/viewer/2022012506/61823f53e60c1062c67d4366/html5/thumbnails/19.jpg)
Panoramic Photography
kolor
![Page 20: EE290T : 3D Reconstruction and Recognition](https://reader031.vdocuments.us/reader031/viewer/2022012506/61823f53e60c1062c67d4366/html5/thumbnails/20.jpg)
30
3D modeling of landmarks
![Page 21: EE290T : 3D Reconstruction and Recognition](https://reader031.vdocuments.us/reader031/viewer/2022012506/61823f53e60c1062c67d4366/html5/thumbnails/21.jpg)
Computer vision and Applications
31
1990 20102000
EosSystems Autostich
• Efficient SLAM/SFM• Large scale image repositories• Deep learning (e.g. ImageNet)
![Page 22: EE290T : 3D Reconstruction and Recognition](https://reader031.vdocuments.us/reader031/viewer/2022012506/61823f53e60c1062c67d4366/html5/thumbnails/22.jpg)
Computer vision and Applications
32
1990 20102000
Kooaba
A9
Kinect
EosSystems Autostich
Google Goggles
![Page 23: EE290T : 3D Reconstruction and Recognition](https://reader031.vdocuments.us/reader031/viewer/2022012506/61823f53e60c1062c67d4366/html5/thumbnails/23.jpg)
Image search engines
![Page 24: EE290T : 3D Reconstruction and Recognition](https://reader031.vdocuments.us/reader031/viewer/2022012506/61823f53e60c1062c67d4366/html5/thumbnails/24.jpg)
Google Goggles34
Visual search and landmarks recognition
![Page 25: EE290T : 3D Reconstruction and Recognition](https://reader031.vdocuments.us/reader031/viewer/2022012506/61823f53e60c1062c67d4366/html5/thumbnails/25.jpg)
35
Visual search and landmarks recognition
![Page 26: EE290T : 3D Reconstruction and Recognition](https://reader031.vdocuments.us/reader031/viewer/2022012506/61823f53e60c1062c67d4366/html5/thumbnails/26.jpg)
36
Augmented reality
• Magic leap• Daqri• Meta
• Etc…
![Page 27: EE290T : 3D Reconstruction and Recognition](https://reader031.vdocuments.us/reader031/viewer/2022012506/61823f53e60c1062c67d4366/html5/thumbnails/27.jpg)
Motion sensing and gesture recognition
37
![Page 28: EE290T : 3D Reconstruction and Recognition](https://reader031.vdocuments.us/reader031/viewer/2022012506/61823f53e60c1062c67d4366/html5/thumbnails/28.jpg)
Autonomous navigation and safety
Mobileye: Vision systems in high-end BMW, GM, Volvo models
But also, Toyota, Google, Apple, Tesla, Nissan, Ford, etc….
Source: A. Shashua, S. Seitz
![Page 29: EE290T : 3D Reconstruction and Recognition](https://reader031.vdocuments.us/reader031/viewer/2022012506/61823f53e60c1062c67d4366/html5/thumbnails/29.jpg)
Personal robotics
39
![Page 30: EE290T : 3D Reconstruction and Recognition](https://reader031.vdocuments.us/reader031/viewer/2022012506/61823f53e60c1062c67d4366/html5/thumbnails/30.jpg)
Computer vision and Applications
Vision for robotics, space exploration
Factory inspectionSurveillanceAssistive technologies
Security
![Page 31: EE290T : 3D Reconstruction and Recognition](https://reader031.vdocuments.us/reader031/viewer/2022012506/61823f53e60c1062c67d4366/html5/thumbnails/31.jpg)
411990 20102000
Computer vision and Applications
Kooaba
A9
Kinect
EosSystems Autostich
Google Goggles
![Page 32: EE290T : 3D Reconstruction and Recognition](https://reader031.vdocuments.us/reader031/viewer/2022012506/61823f53e60c1062c67d4366/html5/thumbnails/32.jpg)
EosSystems
Computer vision and Applications
421990 20102000
2D
3D
Google Goggles
![Page 33: EE290T : 3D Reconstruction and Recognition](https://reader031.vdocuments.us/reader031/viewer/2022012506/61823f53e60c1062c67d4366/html5/thumbnails/33.jpg)
Computer vision and Applications
431990
EosSystems
20102000
2D
3D
Google Goggles
![Page 34: EE290T : 3D Reconstruction and Recognition](https://reader031.vdocuments.us/reader031/viewer/2022012506/61823f53e60c1062c67d4366/html5/thumbnails/34.jpg)
Current state of computer vision
3D Reconstruction• 3D shape recovery• 3D scene reconstruction• Camera localization• Pose estimation
2D Recognition• Object detection• Texture classification• Target tracking• Activity recognition
4 4
![Page 35: EE290T : 3D Reconstruction and Recognition](https://reader031.vdocuments.us/reader031/viewer/2022012506/61823f53e60c1062c67d4366/html5/thumbnails/35.jpg)
3D Reconstruction• 3D shape recovery• 3D scene reconstruction• Camera localization• Pose estimation
Current state of computer vision
Levoy et al., 00Hartley & Zisserman, 00Dellaert et al., 00Rusinkiewic et al., 02Nistér, 04Brown & Lowe, 04Schindler et al, 04Lourakis & Argyros, 04Colombo et al. 05
Golparvar-Fard, et al. JAEI 10Pandey et al. IFAC , 2010Pandey et al. ICRA 2011Savarese et al. IJCV 05Savarese et al. IJCV 06Microsoft’s PhotoSynth Snavely et al., 06-08Schindler et al., 08Agarwal et al., 09 45Frahm et al., 10
Lucas & Kanade, 81Chen & Medioni, 92Debevec et al., 96Levoy & Hanrahan, 96Fitzgibbon & Zisserman, 98Triggs et al., 99Pollefeys et al., 99Kutulakos & Seitz, 99
Snavely
et al., 06
-08
![Page 36: EE290T : 3D Reconstruction and Recognition](https://reader031.vdocuments.us/reader031/viewer/2022012506/61823f53e60c1062c67d4366/html5/thumbnails/36.jpg)
3D Reconstruction• 3D shape recovery• 3D scene reconstruction• Camera localization• Pose estimation
Current state of computer vision
Levoy et al., 00Hartley & Zisserman, 00Dellaert et al., 00Rusinkiewic et al., 02Nistér, 04Brown & Lowe, 04Schindler et al, 04Lourakis & Argyros, 04Colombo et al. 05
Golparvar-Fard, et al. JAEI 10Pandey et al. IFAC , 2010Pandey et al. ICRA 2011Savarese et al. IJCV 05Savarese et al. IJCV 06Microsoft’s PhotoSynth Snavely et al., 06-08Schindler et al., 08Agarwal et al., 09Frahm et al., 10
Lucas & Kanade, 81Chen & Medioni, 92Debevec et al., 96Levoy & Hanrahan, 96Fitzgibbon & Zisserman, 98Triggs et al., 99Pollefeys et al., 99Kutulakos & Seitz, 99
Snavely
et al., 06
-08
![Page 37: EE290T : 3D Reconstruction and Recognition](https://reader031.vdocuments.us/reader031/viewer/2022012506/61823f53e60c1062c67d4366/html5/thumbnails/37.jpg)
2D Recognition• Object detection• Texture classification• Target tracking• Activity recognition
Current state of computer vision
Turk & Pentland, 91Poggio et al., 93Belhumeur et al., 97LeCun et al. 98 Amit and Geman, 99 Shi& Malik, 00 Viola & Jones, 00Felzenszwalb & Huttenlocher 00Belongie & Malik, 02Ullman et al. 02
Argawal & Roth, 02Ramanan & Forsyth, 03Weber et al., 00Vidal-Naquet & Ullman 02Fergus et al., 03Torralba et al., 03Vogel & Schiele, 03Barnard et al., 03Fei-Fei et al., 04Kumar & Hebert ‘04
He et al. 06Gould et al. 08Maire et al. 08Felzenszwalb et al., 08Kohli et al. 09L.-J. Li et al. 09Ladicky et al. 10,11Gonfaus et al. 10Farhadi et al., 09Lampert et al., 09 47
![Page 38: EE290T : 3D Reconstruction and Recognition](https://reader031.vdocuments.us/reader031/viewer/2022012506/61823f53e60c1062c67d4366/html5/thumbnails/38.jpg)
2D Recognition• Object detection• Texture classification• Target tracking• Activity recognition
Current state of computer vision
car person car
Car Car
Street
Tree
PersonBike
Building
Turk & Pentland, 91Poggio et al., 93Belhumeur et al., 97LeCun et al. 98 Amit and Geman, 99 Shi& Malik, 00 Viola & Jones, 00Felzenszwalb & Huttenlocher 00Belongie & Malik, 02Ullman et al. 02
Argawal & Roth, 02Ramanan & Forsyth, 03Weber et al., 00Vidal-Naquet & Ullman 02Fergus et al., 03Torralba et al., 03Vogel & Schiele, 03Barnard et al., 03Fei-Fei et al., 04Kumar & Hebert ‘04
He et al. 06Gould et al. 08Maire et al. 08Felzenszwalb et al., 08Kohli et al. 09L.-J. Li et al. 09Ladicky et al. 10,11Gonfaus et al. 10Farhadi et al., 09Lampert et al., 09
![Page 39: EE290T : 3D Reconstruction and Recognition](https://reader031.vdocuments.us/reader031/viewer/2022012506/61823f53e60c1062c67d4366/html5/thumbnails/39.jpg)
49
Current state of computer vision
3D Reconstruction• 3D shape recovery• 3D scene reconstruction• Camera localization• Pose estimation
2D Recognition• Object detection• Texture classification• Target tracking• Activity recognition
Perceiving the World in 3D!
![Page 40: EE290T : 3D Reconstruction and Recognition](https://reader031.vdocuments.us/reader031/viewer/2022012506/61823f53e60c1062c67d4366/html5/thumbnails/40.jpg)
Course overview
1. Geometry
2. Semantics
Geometry:- How to extract 3d information?- Which cues are useful?- What are the mathematical tools?
![Page 41: EE290T : 3D Reconstruction and Recognition](https://reader031.vdocuments.us/reader031/viewer/2022012506/61823f53e60c1062c67d4366/html5/thumbnails/41.jpg)
Camera systemsEstablish a mapping from 3D to 2D
![Page 42: EE290T : 3D Reconstruction and Recognition](https://reader031.vdocuments.us/reader031/viewer/2022012506/61823f53e60c1062c67d4366/html5/thumbnails/42.jpg)
How to calibrate a cameraEstimate camera parameters such as pose or focallength
?
![Page 43: EE290T : 3D Reconstruction and Recognition](https://reader031.vdocuments.us/reader031/viewer/2022012506/61823f53e60c1062c67d4366/html5/thumbnails/43.jpg)
Single view metrologyEstimate 3D properties of the world from a single image
?
![Page 44: EE290T : 3D Reconstruction and Recognition](https://reader031.vdocuments.us/reader031/viewer/2022012506/61823f53e60c1062c67d4366/html5/thumbnails/44.jpg)
Single view metrologyEstimate 3D properties of the world from a single image
![Page 45: EE290T : 3D Reconstruction and Recognition](https://reader031.vdocuments.us/reader031/viewer/2022012506/61823f53e60c1062c67d4366/html5/thumbnails/45.jpg)
Multiple view geometryEstimate 3D properties of the world from multiple views
![Page 46: EE290T : 3D Reconstruction and Recognition](https://reader031.vdocuments.us/reader031/viewer/2022012506/61823f53e60c1062c67d4366/html5/thumbnails/46.jpg)
Toma si & Kana de (1993)
Mathematical tools
Epipola r geometry
Photoconsistency
![Page 47: EE290T : 3D Reconstruction and Recognition](https://reader031.vdocuments.us/reader031/viewer/2022012506/61823f53e60c1062c67d4366/html5/thumbnails/47.jpg)
Structure from motion
Courtesy of Oxford Visua l Geometry Group
![Page 48: EE290T : 3D Reconstruction and Recognition](https://reader031.vdocuments.us/reader031/viewer/2022012506/61823f53e60c1062c67d4366/html5/thumbnails/48.jpg)
Structure lighting and volumetric stereo
Scanning Michelangelo’s “The David”• The Digital Michelangelo Project
- http://graphics.stanford.edu/projects/mich/
• 2 BILLION polygons, accuracy to .29mm
![Page 49: EE290T : 3D Reconstruction and Recognition](https://reader031.vdocuments.us/reader031/viewer/2022012506/61823f53e60c1062c67d4366/html5/thumbnails/49.jpg)
Course overview
1. Geometry
2. Semantics
Semantics:- How to recognize objects?- How to classify images or understand a scene?- How to segment out critical semantics- How to estimate 3D properties (pose, size, shape…)
![Page 50: EE290T : 3D Reconstruction and Recognition](https://reader031.vdocuments.us/reader031/viewer/2022012506/61823f53e60c1062c67d4366/html5/thumbnails/50.jpg)
Object recognition and categorization
![Page 51: EE290T : 3D Reconstruction and Recognition](https://reader031.vdocuments.us/reader031/viewer/2022012506/61823f53e60c1062c67d4366/html5/thumbnails/51.jpg)
Classification:Is this an forest?
No!
![Page 52: EE290T : 3D Reconstruction and Recognition](https://reader031.vdocuments.us/reader031/viewer/2022012506/61823f53e60c1062c67d4366/html5/thumbnails/52.jpg)
Classification:Does this image contain a building? [yes/no]
Yes!
![Page 53: EE290T : 3D Reconstruction and Recognition](https://reader031.vdocuments.us/reader031/viewer/2022012506/61823f53e60c1062c67d4366/html5/thumbnails/53.jpg)
Detection:Does this image contain a car? [where?]
car
![Page 54: EE290T : 3D Reconstruction and Recognition](https://reader031.vdocuments.us/reader031/viewer/2022012506/61823f53e60c1062c67d4366/html5/thumbnails/54.jpg)
Building
clock
personcar
Detection:Which objects do this image contain? [where?]
![Page 55: EE290T : 3D Reconstruction and Recognition](https://reader031.vdocuments.us/reader031/viewer/2022012506/61823f53e60c1062c67d4366/html5/thumbnails/55.jpg)
clock
Detection:Accurate localization (segmentation)
![Page 56: EE290T : 3D Reconstruction and Recognition](https://reader031.vdocuments.us/reader031/viewer/2022012506/61823f53e60c1062c67d4366/html5/thumbnails/56.jpg)
Building 45 degree
Person, backCar, side view
Detection:Estimating 3D geometrical properties
![Page 57: EE290T : 3D Reconstruction and Recognition](https://reader031.vdocuments.us/reader031/viewer/2022012506/61823f53e60c1062c67d4366/html5/thumbnails/57.jpg)
Challenges: viewpoint variation
slide credit: Fei-Fei, Fergus & Torralba
![Page 58: EE290T : 3D Reconstruction and Recognition](https://reader031.vdocuments.us/reader031/viewer/2022012506/61823f53e60c1062c67d4366/html5/thumbnails/58.jpg)
Challenges: illumination
image credit: J. Koenderink
![Page 59: EE290T : 3D Reconstruction and Recognition](https://reader031.vdocuments.us/reader031/viewer/2022012506/61823f53e60c1062c67d4366/html5/thumbnails/59.jpg)
Challenges: scale
slide credit: Fei-Fei, Fergus & Torralba
![Page 60: EE290T : 3D Reconstruction and Recognition](https://reader031.vdocuments.us/reader031/viewer/2022012506/61823f53e60c1062c67d4366/html5/thumbnails/60.jpg)
Challenges: deformation
![Page 61: EE290T : 3D Reconstruction and Recognition](https://reader031.vdocuments.us/reader031/viewer/2022012506/61823f53e60c1062c67d4366/html5/thumbnails/61.jpg)
Challenges:
occlusion
Magritte, 1957 slide credit: Fei-Fei, Fergus & Torralba
![Page 62: EE290T : 3D Reconstruction and Recognition](https://reader031.vdocuments.us/reader031/viewer/2022012506/61823f53e60c1062c67d4366/html5/thumbnails/62.jpg)
Challenges: background clutter
Kilmeny Niland. 1995
![Page 63: EE290T : 3D Reconstruction and Recognition](https://reader031.vdocuments.us/reader031/viewer/2022012506/61823f53e60c1062c67d4366/html5/thumbnails/63.jpg)
Challenges: object intra-class variation
slide credit: Fei-Fei, Fergus & Torralba
![Page 64: EE290T : 3D Reconstruction and Recognition](https://reader031.vdocuments.us/reader031/viewer/2022012506/61823f53e60c1062c67d4366/html5/thumbnails/64.jpg)
A t. .•
. l , 11t'-:.
I • <\J I . ""'
![Page 65: EE290T : 3D Reconstruction and Recognition](https://reader031.vdocuments.us/reader031/viewer/2022012506/61823f53e60c1062c67d4366/html5/thumbnails/65.jpg)
Course overview
1. Geometry
2. Semantics
Joint recovery of geometry and semantics!
![Page 66: EE290T : 3D Reconstruction and Recognition](https://reader031.vdocuments.us/reader031/viewer/2022012506/61823f53e60c1062c67d4366/html5/thumbnails/66.jpg)
Visua l processing in the bra in
V1
where pathway (dorsal stream)
what pathway (ventral stream)
78
The ventral stream (also known
as the "what pathway") is
involved with object and visual
identification and recognition.
The dorsal stream (or,
"where pathway") is involved
with processing the object's
spatial location relative to
the viewer and with speech
repetition.
![Page 67: EE290T : 3D Reconstruction and Recognition](https://reader031.vdocuments.us/reader031/viewer/2022012506/61823f53e60c1062c67d4366/html5/thumbnails/67.jpg)
V1
where pathway (dorsal stream)
what pathway (ventral stream)
Pre-frontal cortex
79
Visua l processing in the bra in
![Page 68: EE290T : 3D Reconstruction and Recognition](https://reader031.vdocuments.us/reader031/viewer/2022012506/61823f53e60c1062c67d4366/html5/thumbnails/68.jpg)
Joint reconstruction and recognition
…Input images
80 Car Person Tree Sky
Street Building Else
![Page 69: EE290T : 3D Reconstruction and Recognition](https://reader031.vdocuments.us/reader031/viewer/2022012506/61823f53e60c1062c67d4366/html5/thumbnails/69.jpg)
…Input images
81 Car Person Tree Sky
Street Building Else
Joint reconstruction and recognition
![Page 70: EE290T : 3D Reconstruction and Recognition](https://reader031.vdocuments.us/reader031/viewer/2022012506/61823f53e60c1062c67d4366/html5/thumbnails/70.jpg)
“There was a table set out under
a tree in front of the house,and the March Hare and the
Hatter were having tea at it.”
“The table was a large one, but
the three were all crowded
together at one corner of it …”
From “A M a d Tea-Party”
Alice's Adventures in W onderla ndby
Lew is Ca rroll
![Page 71: EE290T : 3D Reconstruction and Recognition](https://reader031.vdocuments.us/reader031/viewer/2022012506/61823f53e60c1062c67d4366/html5/thumbnails/71.jpg)
3D
geo
met
ry
Project presentations
Reco
gnit
ion
Syllabus
Lecture Topic
1 Introduction
2 Camera models
3 Camera calibration
4 Single view metrology
5 Epipolar geometry
6 Multi-view geometry
7 Structure from motion/ SLAM
8 Volumetric stereo
9 Fitting and Matching
10 Detector and Descriptors
11 Intro to Recognition; Object classification I
12 Object classification II
13 Scene understanding & segmentation
14 Visual Representation Learning by NNs
15 3D Object recognition
16 3D Scene understanding