High Quality 3D Reconstruction from Multiple Images
- Title
- High Quality 3D Reconstruction from Multiple Images
- Translated Title
- 다중 이미지를 이용한 고품질 3D 복원 방법
- Authors
- Kyumin Hwang
- DGIST Authors
- Kyumin Hwang; Sunghoon Im; Kyong Hwan Jin
- Advisor(s)
- 임성훈
- Co-Advisor(s)
- Kyong Hwan Jin
- Issue Date
- 2022
- Available Date
- 2022-03-08
- Degree Date
- 2022/02
- Type
- Thesis
- Description
- Multi-view Stereo (MVS), Depth Estimation, Normal Estimation
- Table Of Contents
- I. Introduction 1 II. Related Work 3 III. Proposed method 4 3.1 Initial Depth and Normal Estimation 4 3.2 Cost Volume Warping & Fusion 6 3.3 Geometric Consistency-based Refinement 7 IV. Experiments 9 4.1 Evaluation on Depth Estimation 12 4.2 Evaluation on Normal Estimation 14 V. Ablation Study 15 5.1 Ablation Study on Consistency Map Representation Method 15 5.2 Ablation Study on Multi-view Matching 16 5.3 Ablation Study on Multi-directional Plane Sweep Algorithm 16 5.4 Ablation Study on Novel View Synthesis Application 18 VI. Conclusion 24 VII. References 25 VIII. 요약문 29
- Degree
- Master
- University
- DGIST
- Related Researcher
-
-
Im, Sunghoon Computer Vision Lab.
- Research Interests Computer Vision; Deep Learning; Robot Vision
-
- Files:
There are no files associated with this item.
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.