BEGIN:VCALENDAR VERSION:2.0 PRODID:Linklings LLC BEGIN:VTIMEZONE TZID:Asia/Seoul X-LIC-LOCATION:Asia/Seoul BEGIN:STANDARD TZOFFSETFROM:+0900 TZOFFSETTO:+0900 TZNAME:KST DTSTART:18871231T000000 DTSTART:19881009T020000 END:STANDARD END:VTIMEZONE BEGIN:VEVENT DTSTAMP:20230103T035347Z LOCATION:Room 324\, Level 3\, West Wing DTSTART;TZID=Asia/Seoul:20221207T110000 DTEND;TZID=Asia/Seoul:20221207T123000 UID:siggraphasia_SIGGRAPH Asia 2022_sess158@linklings.com SUMMARY:Acquisition DESCRIPTION:Technical Papers\n\nThe presentations will be followed by a 30 -min Interactive Discussion Session at Room 325-CD.\n\nThe Technical Paper s program is the premier international forum for disseminating new scholar ly work in computer graphics and interactive techniques. Technical Papers are published as a special issue of ACM Transactions on Graphics. In addit ion to papers selected by the SIGGRAPH Asia 2022 Technical Papers Jury, th e conference presents papers that have been published in ACM Transactions on Graphics during the past year. Accepted papers adhere to the highest sc ientific standards.\n\nDeepMVSHair: Deep Hair Modeling from Sparse Views\n \nKuang, Chen, Fu, Zhou, Zheng\n\nWe present DeepMVSHair, the first deep l earning-based method for multi-view hair strand reconstruction. The key co mponent of our pipeline is HairMVSNet, a differentiable neural architectur e which represents a spatial hair structure as a continuous 3D hair growin g direction field implicitly. Specific...\n\n---------------------\nAsynch ronous Collaborative Autoscanning with Mode Switching for Multi-Robot Scen e Reconstruction\n\nGuo, Li, Xia, Hu, Liu\n\nWhen conducting autonomous sc anning for the online reconstruction of unknown indoor environments, robot s have to be competent at exploring the scene structure and reconstructing objects with high quality. Our key observation is that different tasks de mand specialized scanning properties of robots: r...\n\n------------------ ---\nPattern-Based Cloth Registration and Sparse-View Animation\n\nHalimi, Stuyck, Xiang, Bagautdinov, Wen...\n\nWe propose a novel multi-view camer a pipeline for the reconstruction and registration of dynamic clothing.\nO ur proposed method relies on a specifically designed pattern that allows f or precise video tracking in each camera view. \nWe triangulate the tracke d points and register the cloth surface in a ...\n\n---------------------\ nReconstructing Personalized Semantic Facial NeRF Models From Monocular Vi deo\n\nGao, Zhong, Xiang, Hong, Guo...\n\nWe present a novel semantic mode l for human head defined with neural radiance field. The 3D-consistent hea d model consist of a set of disentangled and interpretable bases, and can be driven by low-dimensional expression coefficients. Thanks to the powerf ul representation ability of neural radiance f...\n\n--------------------- \nAffordable Spectral Measurements of Translucent Materials\n\nIser, Ritti g, Nogu�, Nindel, Wilkie\n\nWe present a spectral measurement approach for the bulk optical properties of translucent materials using only low-cost components. We focus on the translucent inks used in full-color 3D printin g, and develop a technique with a high spectral resolution, which is impor tant for accurate color reproduc...\n\n---------------------\nLearning Rec onstructability for Drone Aerial Path Planning\n\nLiu, Lin, Hu, Xie, Fu... \n\nWe introduce the first learning-based reconstructability predictor to improve view and path planning for large-scale 3D urban scene acquisition using unmanned drones. In contrast to previous heuristic approaches, our m ethod learns a model that explicitly predicts how well a 3D urban scene wi ll be re...\n\n\nRegistration Category: FULL ACCESS, ON-DEMAND ACCESS\n\nL anguage: ENGLISH\n\nFormat: IN-PERSON, ON-DEMAND END:VEVENT END:VCALENDAR