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:20230103T035346Z
LOCATION:Room 324\, Level 3\, West Wing
DTSTART;TZID=Asia/Seoul:20221206T140000
DTEND;TZID=Asia/Seoul:20221206T153000
UID:siggraphasia_SIGGRAPH Asia 2022_sess154@linklings.com
SUMMARY:Character Animation
DESCRIPTION:Technical Communications, Technical Papers\n\nThe presentation
 s will be followed by a 30-min Interactive Discussion Session at Room 325-
 CD. \n\nThe Technical Papers program is the premier international forum fo
 r disseminating new scholarly work in computer graphics and interactive te
 chniques. Technical Papers are published as a special issue of ACM Transac
 tions on Graphics. In addition to papers selected by the SIGGRAPH Asia 202
 2 Technical Papers Jury, the conference presents papers that have been pub
 lished in ACM Transactions on Graphics during the past year. Accepted pape
 rs adhere to the highest scientific standards.\n\nThe Technical Communicat
 ions program is a premier forum for presenting the latest developments and
  research still in progress. Leading international experts in academia and
  industry present work that showcase actual implementations of research id
 eas, works at the crossroads of computer graphics with computer vision, ma
 chine learning, HCI, VR, CAD, visualization, and many others.\n\nMotion In
 -betweening via Two-stage Transformers\n\nQin, Zheng, Zhou\n\nWe present a
  deep learning-based framework to synthesize motion in-betweening in a two
 -stage manner. Given some context frames and a target frame, the system ca
 n generate plausible transitions with variable lengths in a non-autoregres
 sive fashion. The framework consists of two Transformer Encoder-ba...\n\n-
 --------------------\nTransformer Inertial Poser: Real-time Human Motion R
 econstruction from Sparse IMUs with Simultaneous Terrain Generation\n\nJia
 ng, Ye, Gopinath, Won, Winkler...\n\nReal-time human motion reconstruction
  from a sparse set of (e.g. six) wearable IMUs provides a non-intrusive an
 d economic approach to motion capture. Without the ability to acquire posi
 tion information directly from IMUs, recent works took data-driven approac
 hes that utilize large human motion datas...\n\n---------------------\nCon
 trol VAE: Model-Based Learning of Generative Controllers for Physics-Based
  Characters\n\nYao, Song, Chen, Liu\n\nIn this paper, we introduce Control
  VAE, a novel model-based framework for learning generative motion control
  policies based on variational autoencoders (VAE). Our framework can learn
  a rich and flexible latent representation of skills and a skill-condition
 ed generative control policy from a diverse...\n\n---------------------\nM
 oRig: Motion-Aware Rigging of Character Meshes from Point Clouds\n\nXu, Zh
 ou, Yi, Kalogerakis\n\nWe present MoRig, a method that automatically rigs 
 character meshes driven by single-view point cloud streams capturing the m
 otion of performing characters. Our method is also able to animate the 3D 
 meshes according to the captured point cloud motion. At the heart of our a
 pproach lies a deep neural ...\n\n---------------------\nQuestSim: Human M
 otion Tracking from Sparse Sensors with Simulated Avatars\n\nWinkler, Won,
  Ye\n\nReal-time tracking of human body motion is crucial for interactive 
 and\nimmersive experiences in AR/VR. However, very limited sensor data abo
 ut\nthe body is available from standalone wearable devices such as HMDs (H
 ead\nMounted Devices) or AR glasses. In this work, we present a reinforcem
 ent\nlearning f...\n\n---------------------\nLearning Virtual Chimeras by 
 Dynamic Motion Reassembly\n\nLEE, Lee, Lee\n\nThe Chimera is a mythologica
 l hybrid creature composed of different animal parts. The chimera’s moveme
 nts are highly dependent on the spatial and temporal alignments of its com
 posing parts. In this paper, we present a novel algorithm that creates and
  animates chimeras by dynamically reassembli...\n\n---------------------\n
 SMPL-IK: Learned Morphology-Aware Inverse Kinematics for AI Driven Artisti
 c Workflows\n\nVoleti, Oreshkin, Bocquelet, Harvey, Ménard...\n\nOur appro
 ach unlocks novel artistic workflows using advanced AI tooling. Animator g
 rabs one of the many pictures available on the web and uses it to initiali
 ze an editable 3D scene.\n\n\nRegistration Category: FULL ACCESS, ON-DEMAN
 D ACCESS\n\nLanguage: ENGLISH\n\nFormat: IN-PERSON, ON-DEMAND
END:VEVENT
END:VCALENDAR