GSCT UVR LAB.
UVR Lab. was formed in Feb. 2001 at GIST to study and develop “Virtual Reality in Smart computing environments” that process multimodal input, perceive user’s intention and emotion, and respond to user’s request through Augmented Reality. Since 2012, UVR Lab moved to KAIST GSCT and restarted with a theme of “FUN in Ubiquitous VR.”
 
작성일 : 15-08-05
[10th ISUVR] Invited Talks (7/31, 2015)
 글쓴이 : UVR
조회 : 4,754  

 Title: Inferring mirror symmetric 3D shapes from sketches

○ Abstract: We describe a system for taking a 2D sketch of a mirror-symmetric 3D shape and lifting the curves to 3D, inferring the symmetry relationship from the original hand-drawn curves. The system takes as input a hand-drawn sketch and generates a set of 3D curves such that their orthogonal projection matches the input sketch. The main contribution is a method which is able to identify the symmetry relationship among the hand-drawn curves even in the presence of ambiguity in the sketch.

 

○ Bio: Prof. Frederic Cordier

- 1999 to 2004 : Research Assistant, University of Geneva, Switzerland

- 2004 to 2007 : Visiting Professor, KAIST, South Korea

- Since 2007 : Associate Professor, University of Haute Alsace, University of Strasbourg, France

 

 

 

○ Title: Feature-based matching of animated meshes

○ Abstract: We propose a novel, efficient deforming shape analysis and correspondence framework for animated meshes based on their dynamic and motion properties. We elaborate our method by exploiting a profitable set of motion data exhibited by deforming meshes with time-varying embedding. The main idea of our approach is based on an observation that a dynamic, deforming shape of a given subject contains much more information than a single static posture of it. This distinguishes our method from the existing methods which rely on static shape information for shape correspondence and analysis. Our framework of deforming shape analysis and correspondence of animated meshes is comprised of several major contributions: a new dynamic feature detection technique based on multi-scale animated meshs deformation characteristics, novel dynamic feature descriptor, and an adaptation of a robust graph-based feature correspondence approach followed by the fine matching of the animated meshes. We further use dynamic feature correspondences on the source and target to guide an iterative fine matching of animated meshes in spherical parameterization. We demonstrate advantages of our methods on different animated meshes of varying subjects, movements, complexities and details. 

 

○ Bio: Hyewon Seo, Ph.D.

- 1996 KAIST 전산학 학사 

- 1998 KAIST 전산학 석사 

- 2004년 스위스 제네바 대학교 전산학 박사

- 2004-2009년 충남대학교 컴퓨터공학과 박사

- 2009-현재: 프랑스 CNRS-스트라스부르 대학교

- 최근 주요 경력: 2012-2016 CNRS 위원회, 2014- CAVW associate editor, 2015 Computer Graphics Int'l 학회장 등

- 관심분야: 인체 모델링, 예제 기반 모델링, Mesh registration & segmentation, sketch 기반 모델링 등