Scene Reconstruction, SLAM with RGB-D Data 1. Scene Reconstruction, SLAM with RGB-D Data Yu Huang yu.huang07@gmail.com Sunnyvale, California 2. Outline • Time of Flight • Structured Light • KinectFusion • Combination of Feature + ICP • RGB-D Visual Odometry (VO) • Kintinous: Extended KinectFusion • Combination of FOVIS & RGB-D VO • Dense Visual SLAM • RTAB-Map • ElasticFusion • OminiKinect • Shake
Project page: http://research.microsoft.com/en-us/projects/depth4free/default.aspx We present a machine learning technique for estimating absolute, per-pixel depth using any conventional monocular 2D camera, with minor hardware modifications. Our approach targets close-range human capture and interaction where dense 3D estimation of hands and faces is desired. We use hybrid classification-regress
faceshift is accurate, effortless, and affordable markerless facial performance capture. faceshift uses depth cameras such as Microsoft's Kinect to animate rigs in real time. faceshift works seamlessly for fast facial expressions, head motions, and difficult environments. news Open BetaWe started the open beta, get your free faceshift version and send us your feedback, such that we can focus on wh
リリース、障害情報などのサービスのお知らせ
最新の人気エントリーの配信
処理を実行中です
j次のブックマーク
k前のブックマーク
lあとで読む
eコメント一覧を開く
oページを開く