Publications
Detailed Information
Indoor Image Surface Normal Estimation Using Convolutional Neural Network : 합성곱 신경망을 이용한 실내 이미지에서의 표면 노말 추정
DC Field | Value | Language |
---|---|---|
dc.contributor.advisor | 고형석 | - |
dc.contributor.author | 이원준 | - |
dc.date.accessioned | 2018-05-29T03:28:37Z | - |
dc.date.available | 2018-05-29T03:28:37Z | - |
dc.date.issued | 2018-02 | - |
dc.identifier.other | 000000150718 | - |
dc.identifier.uri | https://hdl.handle.net/10371/141516 | - |
dc.description | 학위논문 (석사)-- 서울대학교 대학원 : 공과대학 전기·정보공학부, 2018. 2. 고형석. | - |
dc.description.abstract | A surface normal vector is related to material of object, shape of geometry, re-
flection of light. To estimate other features, the surface normal vector is necessary. Therefore, the surface normal estimation problem is one of the most important topic in inverse graphics. Previously, computing surface normal image from single RGB-D image has been stud- ied since estimating surface normal vector from single RGB image is extremely ill- posed problem. Recently, deep learning based approach has been presented for the task. However, it is not well-known that which deep learning model is efficiently solve the problem. Also there are limitations in dataset computed from real RGB-D images. In this thesis, first we describes the problems in previous works | - |
dc.description.abstract | the dataset. Sec-
ond, we suggest a way to overcome the limitation of previous work | - |
dc.description.abstract | synthetic dataset.
Lastly, we test several neural net model with set of experiments to find the most proper model. After that we train the neural network model with synthetic dataset. The models prediction of surface normal image looks plausible. Numerically the trained model achieve lower error compared to previous works. | - |
dc.description.tableofcontents | 1 INTRODUCTION 1
2 BACKGROUND AND RELATED WORKS 3 2.1 Convolutional Network 3 2.2 Convolutional Network Nodels 4 2.3 Single Image Surface Normal Estimation 7 2.4 Synthetic Dataset 8 3 METHODS 10 3.1 Training Data 10 3.2 Preprocessing 13 3.3 Training Setup 15 3.4 Loss Function 16 3.5 Neural Network 17 4 EXPERIMENT RESULTS 19 4.1 Loss Comparison 21 4.2 Model Comparison with Partial Dataset 21 4.3 Model Comparison with Full Dataset 24 5 CONCLUSION 27 Abstract (In Korean) 31 | - |
dc.format | application/pdf | - |
dc.format.extent | 10981976 bytes | - |
dc.format.medium | application/pdf | - |
dc.language.iso | en | - |
dc.publisher | 서울대학교 대학원 | - |
dc.subject | 딥러닝 | - |
dc.subject | 컴퓨터 비전 | - |
dc.subject | 컴퓨터 그래픽스 | - |
dc.subject.ddc | 621.3 | - |
dc.title | Indoor Image Surface Normal Estimation Using Convolutional Neural Network | - |
dc.title.alternative | 합성곱 신경망을 이용한 실내 이미지에서의 표면 노말 추정 | - |
dc.type | Thesis | - |
dc.contributor.AlternativeAuthor | Wonjun Lee | - |
dc.description.degree | Master | - |
dc.contributor.affiliation | 공과대학 전기·정보공학부 | - |
dc.date.awarded | 2018-02 | - |
- Appears in Collections:
- Files in This Item:
Item View & Download Count
Items in S-Space are protected by copyright, with all rights reserved, unless otherwise indicated.