A Modular Framework for Image-based 3D Reconstruction

Slide 1

Slide 1 text

Problem Deﬁnition The Process of 3D Reconstruction Framework Design and Implementation Using the Framework for SfM A Modular Framework for Image-based 3D Reconstruction Carsten Brandt May 18, 2017 Master’s thesis Carsten Brandt A Modular Framework for Image-based 3D Reconstruction May 18, 2017 1 / 24

Slide 2

Slide 2 text

Problem Deﬁnition The Process of 3D Reconstruction Framework Design and Implementation Using the Framework for SfM 3D Reconstruction Carsten Brandt A Modular Framework for Image-based 3D Reconstruction May 18, 2017 2 / 24

Slide 3

Slide 3 text

Problem Deﬁnition The Process of 3D Reconstruction Framework Design and Implementation Using the Framework for SfM 3D Reconstruction Structure from Motion (SfM) Carsten Brandt A Modular Framework for Image-based 3D Reconstruction May 18, 2017 2 / 24

Slide 4

Slide 4 text

Slide 5

Slide 5 text

Slide 6

Slide 6 text

Slide 7

Slide 7 text

Problem Deﬁnition The Process of 3D Reconstruction Framework Design and Implementation Using the Framework for SfM Table of Contents 1 Problem Deﬁnition 2 The Process of 3D Reconstruction 3 Framework Design and Implementation 4 Using the Framework for SfM Carsten Brandt A Modular Framework for Image-based 3D Reconstruction May 18, 2017 3 / 24

Slide 8

Slide 8 text

Slide 9

Slide 9 text

Problem Deﬁnition The Process of 3D Reconstruction Framework Design and Implementation Using the Framework for SfM Problem Deﬁnition Carsten Brandt A Modular Framework for Image-based 3D Reconstruction May 18, 2017 5 / 24

Slide 10

Slide 10 text

Problem Deﬁnition The Process of 3D Reconstruction Framework Design and Implementation Using the Framework for SfM Problem Deﬁnition ? Carsten Brandt A Modular Framework for Image-based 3D Reconstruction May 18, 2017 5 / 24

Slide 11

Slide 11 text

Problem Deﬁnition The Process of 3D Reconstruction Framework Design and Implementation Using the Framework for SfM Problem Deﬁnition ? Keypoint Detection Carsten Brandt A Modular Framework for Image-based 3D Reconstruction May 18, 2017 5 / 24

Slide 12

Slide 12 text

Problem Deﬁnition The Process of 3D Reconstruction Framework Design and Implementation Using the Framework for SfM Problem Deﬁnition ? Keypoint Detection Image Matching Carsten Brandt A Modular Framework for Image-based 3D Reconstruction May 18, 2017 5 / 24

Slide 13

Slide 13 text

Problem Deﬁnition The Process of 3D Reconstruction Framework Design and Implementation Using the Framework for SfM Problem Deﬁnition ? Keypoint Detection Image Matching Geometry Estimation Carsten Brandt A Modular Framework for Image-based 3D Reconstruction May 18, 2017 5 / 24

Slide 14

Slide 14 text

Problem Deﬁnition The Process of 3D Reconstruction Framework Design and Implementation Using the Framework for SfM Problem Deﬁnition ? Keypoint Detection Image Matching Geometry Estimation Triangulation Carsten Brandt A Modular Framework for Image-based 3D Reconstruction May 18, 2017 5 / 24

Slide 15

Slide 15 text

Problem Deﬁnition The Process of 3D Reconstruction Framework Design and Implementation Using the Framework for SfM Problem Deﬁnition ? Keypoint Detection Image Matching Geometry Estimation Triangulation . . . Carsten Brandt A Modular Framework for Image-based 3D Reconstruction May 18, 2017 5 / 24

Slide 16

Slide 16 text

Problem Deﬁnition The Process of 3D Reconstruction Framework Design and Implementation Using the Framework for SfM Problem Deﬁnition Keypoint Detection Image Matching Geometry Estimation Triangulation . . . Processing Chain Carsten Brandt A Modular Framework for Image-based 3D Reconstruction May 18, 2017 5 / 24

Slide 17

Slide 17 text

Problem Deﬁnition The Process of 3D Reconstruction Framework Design and Implementation Using the Framework for SfM Existing implementations Existing implementations: Carsten Brandt A Modular Framework for Image-based 3D Reconstruction May 18, 2017 6 / 24

Slide 18

Slide 18 text

Slide 19

Slide 19 text

Problem Definition The Process of 3D Reconstruction Framework Design and Implementation Using the Framework for SfM Existing implementations Existing implementations: single program for everything not flexible for different use case Carsten Brandt A Modular Framework for Image-based 3D Reconstruction May 18, 2017 6 / 24

Slide 20

Slide 20 text

Problem Definition The Process of 3D Reconstruction Framework Design and Implementation Using the Framework for SfM Existing implementations Existing implementations: single program for everything not flexible for different use case hard to adjust/improve Carsten Brandt A Modular Framework for Image-based 3D Reconstruction May 18, 2017 6 / 24

Slide 21

Slide 21 text

Problem Definition The Process of 3D Reconstruction Framework Design and Implementation Using the Framework for SfM Existing implementations Existing implementations: single program for everything not flexible for different use case hard to adjust/improve Carsten Brandt A Modular Framework for Image-based 3D Reconstruction May 18, 2017 6 / 24

Slide 22

Slide 22 text

Problem Definition The Process of 3D Reconstruction Framework Design and Implementation Using the Framework for SfM Existing implementations Existing implementations: single program for everything not flexible for different use case hard to adjust/improve Framework goals: Carsten Brandt A Modular Framework for Image-based 3D Reconstruction May 18, 2017 6 / 24

Slide 23

Slide 23 text

Problem Definition The Process of 3D Reconstruction Framework Design and Implementation Using the Framework for SfM Existing implementations Existing implementations: single program for everything not flexible for different use case hard to adjust/improve Framework goals: flexible processing chain creation Carsten Brandt A Modular Framework for Image-based 3D Reconstruction May 18, 2017 6 / 24

Slide 24

Slide 24 text

Problem Definition The Process of 3D Reconstruction Framework Design and Implementation Using the Framework for SfM Existing implementations Existing implementations: single program for everything not flexible for different use case hard to adjust/improve Framework goals: flexible processing chain creation applicable to large reconstruction problems Carsten Brandt A Modular Framework for Image-based 3D Reconstruction May 18, 2017 6 / 24

Slide 25

Slide 25 text

Problem Definition The Process of 3D Reconstruction Framework Design and Implementation Using the Framework for SfM Existing implementations Existing implementations: single program for everything not flexible for different use case hard to adjust/improve Framework goals: flexible processing chain creation applicable to large reconstruction problems visualisation options Carsten Brandt A Modular Framework for Image-based 3D Reconstruction May 18, 2017 6 / 24

Slide 26

Slide 26 text

Problem Definition The Process of 3D Reconstruction Framework Design and Implementation Using the Framework for SfM Existing implementations Existing implementations: single program for everything not flexible for different use case hard to adjust/improve Framework goals: flexible processing chain creation applicable to large reconstruction problems visualisation options Carsten Brandt A Modular Framework for Image-based 3D Reconstruction May 18, 2017 6 / 24

Slide 27

Slide 27 text

Problem Deﬁnition The Process of 3D Reconstruction Framework Design and Implementation Using the Framework for SfM Structure from Motion Image-based 3D Reconstruction Table of Contents 1 Problem Deﬁnition 2 The Process of 3D Reconstruction 3 Framework Design and Implementation 4 Using the Framework for SfM Carsten Brandt A Modular Framework for Image-based 3D Reconstruction May 18, 2017 7 / 24

Slide 28

Slide 28 text

Slide 29

Slide 29 text

Slide 30

Slide 30 text

Problem Deﬁnition The Process of 3D Reconstruction Framework Design and Implementation Using the Framework for SfM Structure from Motion Image-based 3D Reconstruction Preprocessing Keypoint Detection Images Images +Metadata Images +Metadata +Keypoints Carsten Brandt A Modular Framework for Image-based 3D Reconstruction May 18, 2017 8 / 24

Slide 31

Slide 31 text

Problem Deﬁnition The Process of 3D Reconstruction Framework Design and Implementation Using the Framework for SfM Structure from Motion Image-based 3D Reconstruction Preprocessing Keypoint Detection Keypoint Description Images Images +Metadata Images +Metadata +Keypoints Carsten Brandt A Modular Framework for Image-based 3D Reconstruction May 18, 2017 8 / 24

Slide 32

Slide 32 text

Problem Deﬁnition The Process of 3D Reconstruction Framework Design and Implementation Using the Framework for SfM Structure from Motion Image-based 3D Reconstruction Preprocessing Keypoint Detection Keypoint Description Images Images +Metadata Images +Metadata +Keypoints Feature Extraction Carsten Brandt A Modular Framework for Image-based 3D Reconstruction May 18, 2017 8 / 24

Slide 33

Slide 33 text

Problem Deﬁnition The Process of 3D Reconstruction Framework Design and Implementation Using the Framework for SfM Structure from Motion Image-based 3D Reconstruction Preprocessing Keypoint Detection Keypoint Description Images Images +Metadata Images +Metadata +Keypoints Images +Metadata +Keypoints Feature Extraction Carsten Brandt A Modular Framework for Image-based 3D Reconstruction May 18, 2017 8 / 24

Slide 34

Slide 34 text

Problem Deﬁnition The Process of 3D Reconstruction Framework Design and Implementation Using the Framework for SfM Structure from Motion Image-based 3D Reconstruction Preprocessing Keypoint Detection Keypoint Description Keypoint Matching Images Images +Metadata Images +Metadata +Keypoints Images +Metadata +Keypoints Feature Extraction Carsten Brandt A Modular Framework for Image-based 3D Reconstruction May 18, 2017 8 / 24

Slide 35

Slide 35 text

Problem Deﬁnition The Process of 3D Reconstruction Framework Design and Implementation Using the Framework for SfM Structure from Motion Image-based 3D Reconstruction Preprocessing Keypoint Detection Keypoint Description Keypoint Matching Images Images +Metadata Images +Metadata +Keypoints Images +Metadata +Keypoints Image Graph Feature Extraction Carsten Brandt A Modular Framework for Image-based 3D Reconstruction May 18, 2017 8 / 24

Slide 36

Slide 36 text

Problem Deﬁnition The Process of 3D Reconstruction Framework Design and Implementation Using the Framework for SfM Structure from Motion Image-based 3D Reconstruction Preprocessing Keypoint Detection Keypoint Description Image Clustering Keypoint Matching Images Images +Metadata Images +Metadata +Keypoints Images +Metadata +Keypoints Image Cluster Image Graph Feature Extraction Carsten Brandt A Modular Framework for Image-based 3D Reconstruction May 18, 2017 8 / 24

Slide 37

Slide 37 text

Problem Deﬁnition The Process of 3D Reconstruction Framework Design and Implementation Using the Framework for SfM Structure from Motion Image-based 3D Reconstruction Preprocessing Keypoint Detection Keypoint Description Image Clustering Keypoint Matching Match Filtering Images Images +Metadata Images +Metadata +Keypoints Images +Metadata +Keypoints Image Cluster Image Graph Feature Extraction Carsten Brandt A Modular Framework for Image-based 3D Reconstruction May 18, 2017 8 / 24

Slide 38

Slide 38 text

Problem Deﬁnition The Process of 3D Reconstruction Framework Design and Implementation Using the Framework for SfM Structure from Motion Image-based 3D Reconstruction Preprocessing Keypoint Detection Keypoint Description Image Clustering Keypoint Matching Match Filtering Images Images +Metadata Images +Metadata +Keypoints Images +Metadata +Keypoints Image Cluster Image Graph Feature Extraction Feature Matching Carsten Brandt A Modular Framework for Image-based 3D Reconstruction May 18, 2017 8 / 24

Slide 39

Slide 39 text

Problem Deﬁnition The Process of 3D Reconstruction Framework Design and Implementation Using the Framework for SfM Structure from Motion Image-based 3D Reconstruction Preprocessing Keypoint Detection Keypoint Description Image Clustering Keypoint Matching Match Filtering Images Images +Metadata Images +Metadata +Keypoints Images +Metadata +Keypoints Image Cluster Image Graph Feature Extraction Feature Matching Carsten Brandt A Modular Framework for Image-based 3D Reconstruction May 18, 2017 8 / 24

Slide 40

Slide 40 text

Problem Deﬁnition The Process of 3D Reconstruction Framework Design and Implementation Using the Framework for SfM Structure from Motion Image-based 3D Reconstruction Preprocessing Keypoint Detection Keypoint Description Image Clustering Keypoint Matching Match Filtering Images Images +Metadata Images +Metadata +Keypoints Images +Metadata +Keypoints Image Cluster Image Graph Image Pair Feature Extraction Feature Matching Carsten Brandt A Modular Framework for Image-based 3D Reconstruction May 18, 2017 8 / 24

Slide 41

Slide 41 text

Problem Deﬁnition The Process of 3D Reconstruction Framework Design and Implementation Using the Framework for SfM Structure from Motion Image-based 3D Reconstruction Preprocessing Keypoint Detection Keypoint Description Image Clustering Keypoint Matching Match Filtering Images Images +Metadata Images +Metadata +Keypoints Images +Metadata +Keypoints Image Cluster Image Graph Image Pair +F Feature Extraction Feature Matching Carsten Brandt A Modular Framework for Image-based 3D Reconstruction May 18, 2017 8 / 24

Slide 42

Slide 42 text

Problem Deﬁnition The Process of 3D Reconstruction Framework Design and Implementation Using the Framework for SfM Structure from Motion Image-based 3D Reconstruction Preprocessing Keypoint Detection Keypoint Description Image Clustering Keypoint Matching Match Filtering Images Images +Metadata Images +Metadata +Keypoints Images +Metadata +Keypoints Image Cluster Image Graph Image Pair +F 3D Geometry Estimation Feature Extraction Feature Matching Carsten Brandt A Modular Framework for Image-based 3D Reconstruction May 18, 2017 8 / 24

Slide 43

Slide 43 text

Problem Deﬁnition The Process of 3D Reconstruction Framework Design and Implementation Using the Framework for SfM Structure from Motion Image-based 3D Reconstruction Preprocessing Keypoint Detection Keypoint Description Image Clustering Keypoint Matching Match Filtering Images Images +Metadata Images +Metadata +Keypoints Images +Metadata +Keypoints Image Cluster Image Graph Image Pair +F 3D Geometry Estimation Feature Extraction Feature Matching Carsten Brandt A Modular Framework for Image-based 3D Reconstruction May 18, 2017 8 / 24

Slide 44

Slide 44 text

Problem Deﬁnition The Process of 3D Reconstruction Framework Design and Implementation Using the Framework for SfM Structure from Motion Image-based 3D Reconstruction Preprocessing Keypoint Detection Keypoint Description Image Clustering Keypoint Matching Match Filtering Images Images +Metadata Images +Metadata +Keypoints Images +Metadata +Keypoints Image Cluster Image Graph Image Pair +F 3D Geometry Estimation Images +P Feature Extraction Feature Matching Carsten Brandt A Modular Framework for Image-based 3D Reconstruction May 18, 2017 8 / 24

Slide 45

Slide 45 text

Problem Deﬁnition The Process of 3D Reconstruction Framework Design and Implementation Using the Framework for SfM Structure from Motion Image-based 3D Reconstruction Preprocessing Keypoint Detection Keypoint Description Image Clustering Keypoint Matching Match Filtering Images Images +Metadata Images +Metadata +Keypoints Images +Metadata +Keypoints Image Cluster Image Graph Image Pair +F 3D Geometry Estimation 3D Point Cloud Images +P Feature Extraction Feature Matching Carsten Brandt A Modular Framework for Image-based 3D Reconstruction May 18, 2017 8 / 24

Slide 46

Slide 46 text

Problem Deﬁnition The Process of 3D Reconstruction Framework Design and Implementation Using the Framework for SfM Structure from Motion Image-based 3D Reconstruction Preprocessing Keypoint Detection Keypoint Description Image Clustering Keypoint Matching Match Filtering Images Images +Metadata Images +Metadata +Keypoints Images +Metadata +Keypoints Image Cluster Image Graph Image Pair +F 3D Geometry Estimation 3D Point Cloud Images +P Geometry Reﬁnement Feature Extraction Feature Matching Carsten Brandt A Modular Framework for Image-based 3D Reconstruction May 18, 2017 8 / 24

Slide 47

Slide 47 text

Problem Deﬁnition The Process of 3D Reconstruction Framework Design and Implementation Using the Framework for SfM Structure from Motion Image-based 3D Reconstruction Highlevel overview of image-based 3D reconstruction Images SfM Mesh Carsten Brandt A Modular Framework for Image-based 3D Reconstruction May 18, 2017 9 / 24

Slide 48

Slide 48 text

Problem Deﬁnition The Process of 3D Reconstruction Framework Design and Implementation Using the Framework for SfM Structure from Motion Image-based 3D Reconstruction Highlevel overview of image-based 3D reconstruction Images SfM Images with P Mesh Carsten Brandt A Modular Framework for Image-based 3D Reconstruction May 18, 2017 9 / 24

Slide 49

Slide 49 text

Problem Deﬁnition The Process of 3D Reconstruction Framework Design and Implementation Using the Framework for SfM Structure from Motion Image-based 3D Reconstruction Highlevel overview of image-based 3D reconstruction Images SfM Images with P Image Graph Mesh Carsten Brandt A Modular Framework for Image-based 3D Reconstruction May 18, 2017 9 / 24

Slide 50

Slide 50 text

Problem Deﬁnition The Process of 3D Reconstruction Framework Design and Implementation Using the Framework for SfM Structure from Motion Image-based 3D Reconstruction Highlevel overview of image-based 3D reconstruction Images SfM Images with P Image Graph Sparse Point Cloud Mesh Carsten Brandt A Modular Framework for Image-based 3D Reconstruction May 18, 2017 9 / 24

Slide 51

Slide 51 text

Problem Deﬁnition The Process of 3D Reconstruction Framework Design and Implementation Using the Framework for SfM Structure from Motion Image-based 3D Reconstruction Highlevel overview of image-based 3D reconstruction Images SfM Images with P Image Graph Sparse Point Cloud MVS Mesh Carsten Brandt A Modular Framework for Image-based 3D Reconstruction May 18, 2017 9 / 24

Slide 52

Slide 52 text

Problem Deﬁnition The Process of 3D Reconstruction Framework Design and Implementation Using the Framework for SfM Structure from Motion Image-based 3D Reconstruction Highlevel overview of image-based 3D reconstruction Images SfM Images with P Image Graph Sparse Point Cloud MVS Dense Point Cloud Mesh Carsten Brandt A Modular Framework for Image-based 3D Reconstruction May 18, 2017 9 / 24

Slide 53

Slide 53 text

Problem Deﬁnition The Process of 3D Reconstruction Framework Design and Implementation Using the Framework for SfM Structure from Motion Image-based 3D Reconstruction Highlevel overview of image-based 3D reconstruction Images SfM Images with P Image Graph Sparse Point Cloud MVS Dense Point Cloud Surface Reconstruction Mesh Carsten Brandt A Modular Framework for Image-based 3D Reconstruction May 18, 2017 9 / 24

Slide 54

Slide 54 text

Problem Deﬁnition The Process of 3D Reconstruction Framework Design and Implementation Using the Framework for SfM Structure from Motion Image-based 3D Reconstruction Highlevel overview of image-based 3D reconstruction Images SfM Images with P Image Graph Sparse Point Cloud MVS Dense Point Cloud Surface Reconstruction Mesh Carsten Brandt A Modular Framework for Image-based 3D Reconstruction May 18, 2017 9 / 24

Slide 55

Slide 55 text

Problem Deﬁnition The Process of 3D Reconstruction Framework Design and Implementation Using the Framework for SfM Module Data structure Framework overview Table of Contents 1 Problem Deﬁnition 2 The Process of 3D Reconstruction 3 Framework Design and Implementation 4 Using the Framework for SfM Carsten Brandt A Modular Framework for Image-based 3D Reconstruction May 18, 2017 10 / 24

Slide 56

Slide 56 text

Slide 57

Slide 57 text

Problem Deﬁnition The Process of 3D Reconstruction Framework Design and Implementation Using the Framework for SfM Module Data structure Framework overview Module and Data Module Module Implementation of an Algorithm Data Image,String,Int,... Data type Carsten Brandt A Modular Framework for Image-based 3D Reconstruction May 18, 2017 11 / 24

Slide 58

Slide 58 text

Problem Deﬁnition The Process of 3D Reconstruction Framework Design and Implementation Using the Framework for SfM Module Data structure Framework overview Module and Data Module Module Implementation of an Algorithm inputs Data Image,String,Int,... Data type Carsten Brandt A Modular Framework for Image-based 3D Reconstruction May 18, 2017 11 / 24

Slide 59

Slide 59 text

Slide 60

Slide 60 text

Slide 61

Slide 61 text

Problem Deﬁnition The Process of 3D Reconstruction Framework Design and Implementation Using the Framework for SfM Module Data structure Framework overview Module and Data Module Module Implementation of an Algorithm inputs outputs parameters Data Image,String,Int,... Data type clear interface → reuse of code in diﬀerent contexts Carsten Brandt A Modular Framework for Image-based 3D Reconstruction May 18, 2017 11 / 24

Slide 62

Slide 62 text

Problem Deﬁnition The Process of 3D Reconstruction Framework Design and Implementation Using the Framework for SfM Module Data structure Framework overview Module and Data Module Module Implementation of an Algorithm inputs outputs parameters Data Image,String,Int,... Data type clear interface → reuse of code in diﬀerent contexts self-contained unit → parallelizable Carsten Brandt A Modular Framework for Image-based 3D Reconstruction May 18, 2017 11 / 24

Slide 63

Slide 63 text

Problem Definition The Process of 3D Reconstruction Framework Design and Implementation Using the Framework for SfM Module Data structure Framework overview Module and Data Module Module Implementation of an Algorithm inputs outputs parameters Data Image,String,Int,... Data type clear interface → reuse of code in different contexts self-contained unit → parallelizable common data type implementations → data flow control Carsten Brandt A Modular Framework for Image-based 3D Reconstruction May 18, 2017 11 / 24

Slide 64

Slide 64 text

Problem Definition The Process of 3D Reconstruction Framework Design and Implementation Using the Framework for SfM Module Data structure Framework overview Module and Data Module Module Implementation of an Algorithm inputs outputs parameters Data Image,String,Int,... Data type clear interface → reuse of code in different contexts self-contained unit → parallelizable common data type implementations → data flow control processing chain is a dependency graph Carsten Brandt A Modular Framework for Image-based 3D Reconstruction May 18, 2017 11 / 24

Slide 65

Slide 65 text

Problem Definition The Process of 3D Reconstruction Framework Design and Implementation Using the Framework for SfM Module Data structure Framework overview Processing Chain load module: load image params: filename: image.png resize module: resize image params: width: 1200px height: 900px store module: store image params: filename: resized.png Carsten Brandt A Modular Framework for Image-based 3D Reconstruction May 18, 2017 12 / 24

Slide 66

Slide 66 text

Problem Definition The Process of 3D Reconstruction Framework Design and Implementation Using the Framework for SfM Module Data structure Framework overview Processing Chain load module: load image params: filename: image.png resize module: resize image params: width: 1200px height: 900px store module: store image params: filename: resized.png other1 module: ... params: ... Carsten Brandt A Modular Framework for Image-based 3D Reconstruction May 18, 2017 12 / 24

Slide 67

Slide 67 text

Problem Definition The Process of 3D Reconstruction Framework Design and Implementation Using the Framework for SfM Module Data structure Framework overview Processing Chain load module: load image params: filename: image.png resize module: resize image params: width: 1200px height: 900px store module: store image params: filename: resized.png other1 module: ... params: ... other2 module: ... params: ... Carsten Brandt A Modular Framework for Image-based 3D Reconstruction May 18, 2017 12 / 24

Slide 68

Slide 68 text

Problem Deﬁnition The Process of 3D Reconstruction Framework Design and Implementation Using the Framework for SfM Module Data structure Framework overview Implementation of a Module 1 #include 2 #include 3 4 using namespace u i p f ; 5 6 #define UIPF MODULE ID ” opencv . imgproc . r e s i z e ” 7 #define UIPF MODULE NAME ” Resize Image” 8 #define UIPF MODULE CATEGORY ” opencv ” 9 #define UIPF MODULE CLASS OpenCVResizeImage // . . . Carsten Brandt A Modular Framework for Image-based 3D Reconstruction May 18, 2017 13 / 24

Slide 69

Slide 69 text

Problem Deﬁnition The Process of 3D Reconstruction Framework Design and Implementation Using the Framework for SfM Module Data structure Framework overview Implementation of a Module 1 #include 2 #include 3 4 using namespace u i p f ; 5 6 #define UIPF MODULE ID ” opencv . imgproc . r e s i z e ” 7 #define UIPF MODULE NAME ” Resize Image” 8 #define UIPF MODULE CATEGORY ” opencv ” 9 #define UIPF MODULE CLASS OpenCVResizeImage // . . . Carsten Brandt A Modular Framework for Image-based 3D Reconstruction May 18, 2017 13 / 24

Slide 70

Slide 70 text

Problem Deﬁnition The Process of 3D Reconstruction Framework Design and Implementation Using the Framework for SfM Module Data structure Framework overview Implementation of a Module 1 #include 2 #include 3 4 using namespace u i p f ; 5 6 #define UIPF MODULE ID ” opencv . imgproc . r e s i z e ” 7 #define UIPF MODULE NAME ” Resize Image” 8 #define UIPF MODULE CATEGORY ” opencv ” 9 #define UIPF MODULE CLASS OpenCVResizeImage // . . . Carsten Brandt A Modular Framework for Image-based 3D Reconstruction May 18, 2017 13 / 24

Slide 71

Slide 71 text

Problem Deﬁnition The Process of 3D Reconstruction Framework Design and Implementation Using the Framework for SfM Module Data structure Framework overview Implementation of a Module 11 #define UIPF MODULE INPUTS \ 12 {”image” , DataDescription ( data : : OpenCVMat : : i d ( ) , \ 13 ” the input image . ” )} 14 15 #define UIPF MODULE OUTPUTS \ 16 {”image” , DataDescription ( data : : OpenCVMat : : i d ( ) , \ 17 ” the r e s i z e d image . ” )} 18 19 #define UIPF MODULE PARAMS \ 20 {” width ” , ParamDescription ( ”new width . ” ) } , \ 21 {” he ig h t ” , ParamDescription ( ”new he i g h t . ” ) } 22 23 #include 24 25 void OpenCVResizeImage : : run () { 26 // Module Implementation goes here . 27 } Carsten Brandt A Modular Framework for Image-based 3D Reconstruction May 18, 2017 13 / 24

Slide 72

Slide 72 text

Problem Deﬁnition The Process of 3D Reconstruction Framework Design and Implementation Using the Framework for SfM Module Data structure Framework overview Implementation of a Module 11 #define UIPF MODULE INPUTS \ 12 {”image” , DataDescription ( data : : OpenCVMat : : i d ( ) , \ 13 ” the input image . ” )} 14 15 #define UIPF MODULE OUTPUTS \ 16 {”image” , DataDescription ( data : : OpenCVMat : : i d ( ) , \ 17 ” the r e s i z e d image . ” )} 18 19 #define UIPF MODULE PARAMS \ 20 {” width ” , ParamDescription ( ”new width . ” ) } , \ 21 {” he ig h t ” , ParamDescription ( ”new he i g h t . ” ) } 22 23 #include 24 25 void OpenCVResizeImage : : run () { 26 // Module Implementation goes here . 27 } Carsten Brandt A Modular Framework for Image-based 3D Reconstruction May 18, 2017 13 / 24

Slide 73

Slide 73 text

Problem Deﬁnition The Process of 3D Reconstruction Framework Design and Implementation Using the Framework for SfM Module Data structure Framework overview Implementation of a Module 11 #define UIPF MODULE INPUTS \ 12 {”image” , DataDescription ( data : : OpenCVMat : : i d ( ) , \ 13 ” the input image . ” )} 14 15 #define UIPF MODULE OUTPUTS \ 16 {”image” , DataDescription ( data : : OpenCVMat : : i d ( ) , \ 17 ” the r e s i z e d image . ” )} 18 19 #define UIPF MODULE PARAMS \ 20 {” width ” , ParamDescription ( ”new width . ” ) } , \ 21 {” he ig h t ” , ParamDescription ( ”new he i g h t . ” ) } 22 23 #include 24 25 void OpenCVResizeImage : : run () { 26 // Module Implementation goes here . 27 } Carsten Brandt A Modular Framework for Image-based 3D Reconstruction May 18, 2017 13 / 24

Slide 74

Slide 74 text

Problem Deﬁnition The Process of 3D Reconstruction Framework Design and Implementation Using the Framework for SfM Module Data structure Framework overview Implementation of a Module 11 #define UIPF MODULE INPUTS \ 12 {”image” , DataDescription ( data : : OpenCVMat : : i d ( ) , \ 13 ” the input image . ” )} 14 15 #define UIPF MODULE OUTPUTS \ 16 {”image” , DataDescription ( data : : OpenCVMat : : i d ( ) , \ 17 ” the r e s i z e d image . ” )} 18 19 #define UIPF MODULE PARAMS \ 20 {” width ” , ParamDescription ( ”new width . ” ) } , \ 21 {” he ig h t ” , ParamDescription ( ”new he i g h t . ” ) } 22 23 #include 24 25 void OpenCVResizeImage : : run () { 26 // Module Implementation goes here . 27 } Carsten Brandt A Modular Framework for Image-based 3D Reconstruction May 18, 2017 13 / 24

Slide 75

Slide 75 text

Problem Deﬁnition The Process of 3D Reconstruction Framework Design and Implementation Using the Framework for SfM Module Data structure Framework overview Implementation of a Module 11 #define UIPF MODULE INPUTS \ 12 {”image” , DataDescription ( data : : OpenCVMat : : i d ( ) , \ 13 ” the input image . ” )} 14 15 #define UIPF MODULE OUTPUTS \ 16 {”image” , DataDescription ( data : : OpenCVMat : : i d ( ) , \ 17 ” the r e s i z e d image . ” )} 18 19 #define UIPF MODULE PARAMS \ 20 {” width ” , ParamDescription ( ”new width . ” ) } , \ 21 {” he ig h t ” , ParamDescription ( ”new he i g h t . ” ) } 22 23 #include 24 25 void OpenCVResizeImage : : run () { 26 // Module Implementation goes here . 27 } Carsten Brandt A Modular Framework for Image-based 3D Reconstruction May 18, 2017 13 / 24

Slide 76

Slide 76 text

Problem Deﬁnition The Process of 3D Reconstruction Framework Design and Implementation Using the Framework for SfM Module Data structure Framework overview Implementation of a Module: Data Interface 1 void OpenCVResizeImage : : run () { 2 3 OpenCVMat : : ptr img = getInputData (”image ” ) ; 4 i n t width = getParam(” width ” , −1); 5 i n t h ei gh t = getParam(” he i g h t ” , −1); 6 7 // do something here 8 9 OpenCVMat : : ptr newImage (new OpenCVMat(m) ) ; 10 newImage−>f i l e n a m e = image−>f i l e n a m e ; 11 newImage−>e x i f = image−>e x i f ; 12 setOutputData(”image ” , newImage ) ; 13 14 } Carsten Brandt A Modular Framework for Image-based 3D Reconstruction May 18, 2017 14 / 24

Slide 77

Slide 77 text

Problem Deﬁnition The Process of 3D Reconstruction Framework Design and Implementation Using the Framework for SfM Module Data structure Framework overview Implementation of a Module: Data Interface 1 void OpenCVResizeImage : : run () { 2 3 OpenCVMat : : ptr img = getInputData (”image ” ) ; 4 i n t width = getParam(” width ” , −1); 5 i n t h ei gh t = getParam(” he i g h t ” , −1); 6 7 // do something here 8 9 OpenCVMat : : ptr newImage (new OpenCVMat(m) ) ; 10 newImage−>f i l e n a m e = image−>f i l e n a m e ; 11 newImage−>e x i f = image−>e x i f ; 12 setOutputData(”image ” , newImage ) ; 13 14 } Carsten Brandt A Modular Framework for Image-based 3D Reconstruction May 18, 2017 14 / 24

Slide 78

Slide 78 text

Problem Deﬁnition The Process of 3D Reconstruction Framework Design and Implementation Using the Framework for SfM Module Data structure Framework overview Implementation of a Module: Data Interface 1 void OpenCVResizeImage : : run () { 2 3 OpenCVMat : : ptr img = getInputData (”image ” ) ; 4 i n t width = getParam(” width ” , −1); 5 i n t h ei gh t = getParam(” he i g h t ” , −1); 6 7 // do something here 8 9 OpenCVMat : : ptr newImage (new OpenCVMat(m) ) ; 10 newImage−>f i l e n a m e = image−>f i l e n a m e ; 11 newImage−>e x i f = image−>e x i f ; 12 setOutputData(”image ” , newImage ) ; 13 14 } Carsten Brandt A Modular Framework for Image-based 3D Reconstruction May 18, 2017 14 / 24

Slide 79

Slide 79 text

Problem Deﬁnition The Process of 3D Reconstruction Framework Design and Implementation Using the Framework for SfM Module Data structure Framework overview Implementation of a Module: Data Interface 1 void OpenCVResizeImage : : run () { 2 3 OpenCVMat : : ptr img = getInputData (”image ” ) ; 4 i n t width = getParam(” width ” , −1); 5 i n t h ei gh t = getParam(” he i g h t ” , −1); 6 7 // do something here 8 9 OpenCVMat : : ptr newImage (new OpenCVMat(m) ) ; 10 newImage−>f i l e n a m e = image−>f i l e n a m e ; 11 newImage−>e x i f = image−>e x i f ; 12 setOutputData(”image ” , newImage ) ; 13 14 } Carsten Brandt A Modular Framework for Image-based 3D Reconstruction May 18, 2017 14 / 24

Slide 80

Slide 80 text

Problem Deﬁnition The Process of 3D Reconstruction Framework Design and Implementation Using the Framework for SfM Module Data structure Framework overview Implementation of a Module: Data Interface 1 void OpenCVResizeImage : : run () { 2 3 OpenCVMat : : ptr img = getInputData (”image ” ) ; 4 i n t width = getParam(” width ” , −1); 5 i n t h ei gh t = getParam(” he i g h t ” , −1); 6 7 // do something here 8 9 OpenCVMat : : ptr newImage (new OpenCVMat(m) ) ; 10 newImage−>f i l e n a m e = image−>f i l e n a m e ; 11 newImage−>e x i f = image−>e x i f ; 12 setOutputData(”image ” , newImage ) ; 13 14 } Carsten Brandt A Modular Framework for Image-based 3D Reconstruction May 18, 2017 14 / 24

Slide 81

Slide 81 text

Problem Deﬁnition The Process of 3D Reconstruction Framework Design and Implementation Using the Framework for SfM Module Data structure Framework overview Implementation of a Module: Data Interface 1 void OpenCVResizeImage : : run () { 2 3 OpenCVMat : : ptr img = getInputData (”image ” ) ; 4 i n t width = getParam(” width ” , −1); 5 i n t h ei gh t = getParam(” he i g h t ” , −1); 6 7 // do something here 8 9 OpenCVMat : : ptr newImage (new OpenCVMat(m) ) ; 10 newImage−>f i l e n a m e = image−>f i l e n a m e ; 11 newImage−>e x i f = image−>e x i f ; 12 setOutputData(”image ” , newImage ) ; 13 14 } Carsten Brandt A Modular Framework for Image-based 3D Reconstruction May 18, 2017 14 / 24

Slide 82

Slide 82 text

Problem Deﬁnition The Process of 3D Reconstruction Framework Design and Implementation Using the Framework for SfM Module Data structure Framework overview Data structure implementation Image,String,Int,... Data type Carsten Brandt A Modular Framework for Image-based 3D Reconstruction May 18, 2017 15 / 24

Slide 83

Slide 83 text

Problem Deﬁnition The Process of 3D Reconstruction Framework Design and Implementation Using the Framework for SfM Module Data structure Framework overview Data structure implementation Image,String,Int,... Data type Data structure is a container Carsten Brandt A Modular Framework for Image-based 3D Reconstruction May 18, 2017 15 / 24

Slide 84

Slide 84 text

Problem Deﬁnition The Process of 3D Reconstruction Framework Design and Implementation Using the Framework for SfM Module Data structure Framework overview Data structure implementation Image,String,Int,... Data type Data structure is a container Interface for visualisation and serialisation Carsten Brandt A Modular Framework for Image-based 3D Reconstruction May 18, 2017 15 / 24

Slide 85

Slide 85 text

Problem Deﬁnition The Process of 3D Reconstruction Framework Design and Implementation Using the Framework for SfM Module Data structure Framework overview Data structure implementation Image,String,Int,... Data type Data structure is a container Interface for visualisation and serialisation Custom datatypes possible Carsten Brandt A Modular Framework for Image-based 3D Reconstruction May 18, 2017 15 / 24

Slide 86

Slide 86 text

Problem Deﬁnition The Process of 3D Reconstruction Framework Design and Implementation Using the Framework for SfM Module Data structure Framework overview Framework overview Framework Library Runner Data Manager Logger Module Loader Carsten Brandt A Modular Framework for Image-based 3D Reconstruction May 18, 2017 16 / 24

Slide 87

Slide 87 text

Problem Deﬁnition The Process of 3D Reconstruction Framework Design and Implementation Using the Framework for SfM Module Data structure Framework overview Framework overview Framework Library Runner Data Manager Logger Module Loader Module 1 Module n . . . Carsten Brandt A Modular Framework for Image-based 3D Reconstruction May 18, 2017 16 / 24

Slide 88

Slide 88 text

Problem Deﬁnition The Process of 3D Reconstruction Framework Design and Implementation Using the Framework for SfM Module Data structure Framework overview Framework overview Framework Library Processing Chain YAML File Runner Data Manager Logger Module Loader Module 1 Module n . . . Carsten Brandt A Modular Framework for Image-based 3D Reconstruction May 18, 2017 16 / 24

Slide 89

Slide 89 text

Problem Deﬁnition The Process of 3D Reconstruction Framework Design and Implementation Using the Framework for SfM Module Data structure Framework overview Framework overview GUI CLI Framework Library Processing Chain YAML File Runner Data Manager Logger Module Loader Module 1 Module n . . . Carsten Brandt A Modular Framework for Image-based 3D Reconstruction May 18, 2017 16 / 24

Slide 90

Slide 90 text

Problem Deﬁnition The Process of 3D Reconstruction Framework Design and Implementation Using the Framework for SfM Module Data structure Framework overview GU Interface Carsten Brandt A Modular Framework for Image-based 3D Reconstruction May 18, 2017 17 / 24

Slide 91

Slide 91 text

Slide 92

Slide 92 text

Problem Deﬁnition The Process of 3D Reconstruction Framework Design and Implementation Using the Framework for SfM Module Data structure Framework overview CL Interface # run a p r o c e s s i n g chain u i p f −c processing −chain . yaml # run a s i n g l e module u i p f uipfsfm . keypoint −i image . jpg −o p o i n t s . t x t Carsten Brandt A Modular Framework for Image-based 3D Reconstruction May 18, 2017 18 / 24

Slide 93

Slide 93 text

Problem Deﬁnition The Process of 3D Reconstruction Framework Design and Implementation Using the Framework for SfM Module Data structure Framework overview CL Interface # run a p r o c e s s i n g chain u i p f −c processing −chain . yaml # run a s i n g l e module u i p f uipfsfm . keypoint −i image . jpg −o p o i n t s . t x t # l i s t and document modules u i p f −l u i p f −−i n f o uipfsfm . keypoint . s i f t Carsten Brandt A Modular Framework for Image-based 3D Reconstruction May 18, 2017 18 / 24

Slide 94

Slide 94 text

Problem Deﬁnition The Process of 3D Reconstruction Framework Design and Implementation Using the Framework for SfM Dataset Processing Chain Results Conclusion Table of Contents 1 Problem Deﬁnition 2 The Process of 3D Reconstruction 3 Framework Design and Implementation 4 Using the Framework for SfM Carsten Brandt A Modular Framework for Image-based 3D Reconstruction May 18, 2017 19 / 24

Slide 95

Slide 95 text

Problem Deﬁnition The Process of 3D Reconstruction Framework Design and Implementation Using the Framework for SfM Dataset Processing Chain Results Conclusion Dataset 79 images 2592 × 1728px “Der Hass” dataset by [Fuhrmann 2014] Simon Fuhrmann, Fabian Langguth and Michael Goesele. MVE - A Multi-View Reconstruction Environment. In GCH, pages 1118, 2014. Carsten Brandt A Modular Framework for Image-based 3D Reconstruction May 18, 2017 20 / 24

Slide 96

Slide 96 text

Problem Deﬁnition The Process of 3D Reconstruction Framework Design and Implementation Using the Framework for SfM Dataset Processing Chain Results Conclusion Processing Chain Carsten Brandt A Modular Framework for Image-based 3D Reconstruction May 18, 2017 21 / 24

Slide 97

Slide 97 text

Slide 98

Slide 98 text

Slide 99

Slide 99 text

Problem Deﬁnition The Process of 3D Reconstruction Framework Design and Implementation Using the Framework for SfM Dataset Processing Chain Results Conclusion Sparse Point Cloud Carsten Brandt A Modular Framework for Image-based 3D Reconstruction May 18, 2017 22 / 24

Slide 100

Slide 100 text

Problem Deﬁnition The Process of 3D Reconstruction Framework Design and Implementation Using the Framework for SfM Dataset Processing Chain Results Conclusion Mesh Carsten Brandt A Modular Framework for Image-based 3D Reconstruction May 18, 2017 23 / 24

Slide 101

Slide 101 text

Problem Deﬁnition The Process of 3D Reconstruction Framework Design and Implementation Using the Framework for SfM Dataset Processing Chain Results Conclusion Conclusion Carsten Brandt A Modular Framework for Image-based 3D Reconstruction May 18, 2017 24 / 24

Slide 102

Slide 102 text

Problem Deﬁnition The Process of 3D Reconstruction Framework Design and Implementation Using the Framework for SfM Dataset Processing Chain Results Conclusion Conclusion https://github.com/uipf/uipf Carsten Brandt A Modular Framework for Image-based 3D Reconstruction May 18, 2017 24 / 24