○ 일시: 2023. 4.14(금) 11:00
○ 발표자: 안병주 연구원 (KIST 인공지능연구단 / Carnegie Mellon University)
○ 주제: Kaleidoscopic Imaging for Full-Surround 3D Reconstruction
○ Abstract
- 3D scanning of a single view of an object seldom suffices. Be it for 3D printing, augmented reality, or virtual reality, scanning the shape of the entire object in all its complexity—what we refer to as "full-surround 3D"—is critical to have a faithful digital twin. In this talk, I will introduce a novel system that employs kaleidoscopic imaging for full-surround 3D reconstruction. This system enables us to reconstruct, with high accuracy and full coverage, highly complex objects that have intricate geometric features, including concavities and self-occlusions. Furthermore, I will discuss how the integration of recent neural surface representations can enhance kaleidoscopic imaging, enabling single-shot full-surround 3D reconstruction.
○ Bio
- Byeongjoo Ahn is a Ph.D. Candidate majoring in Electrical and Computer Engineering at Carnegie Mellon University. His research focuses on computational imaging and computer vision, specifically on uncovering hidden visual cues present in our physical environment, such as interreflections, and developing advanced imaging systems that extend human perceptual abilities. Ahn earned his B.S. in Electrical and Computer Engineering and M.S. in Electrical Engineering and Computer Science from Seoul National University. Prior to his current studies, he worked as a research scientist at Korea Institute of Science and Technology (KIST).
○ 일시: 2023. 4.14(금) 11:00
○ 발표자: 안병주 연구원 (KIST 인공지능연구단 / Carnegie Mellon University)
○ 주제: Kaleidoscopic Imaging for Full-Surround 3D Reconstruction
○ Abstract
- 3D scanning of a single view of an object seldom suffices. Be it for 3D printing, augmented reality, or virtual reality, scanning the shape of the entire object in all its complexity—what we refer to as "full-surround 3D"—is critical to have a faithful digital twin. In this talk, I will introduce a novel system that employs kaleidoscopic imaging for full-surround 3D reconstruction. This system enables us to reconstruct, with high accuracy and full coverage, highly complex objects that have intricate geometric features, including concavities and self-occlusions. Furthermore, I will discuss how the integration of recent neural surface representations can enhance kaleidoscopic imaging, enabling single-shot full-surround 3D reconstruction.
○ Bio
- Byeongjoo Ahn is a Ph.D. Candidate majoring in Electrical and Computer Engineering at Carnegie Mellon University. His research focuses on computational imaging and computer vision, specifically on uncovering hidden visual cues present in our physical environment, such as interreflections, and developing advanced imaging systems that extend human perceptual abilities. Ahn earned his B.S. in Electrical and Computer Engineering and M.S. in Electrical Engineering and Computer Science from Seoul National University. Prior to his current studies, he worked as a research scientist at Korea Institute of Science and Technology (KIST).