Reconstructing Articulated Rigged Models from RGB-D Videos
نویسندگان
چکیده
Although commercial and open-source software exist to reconstruct a static object from a sequence recorded with an RGB-D sensor, there is a lack of tools that build rigged models of articulated objects that deform realistically and can be used for tracking or animation. In this work, we fill this gap and propose a method that creates a fully rigged model of an articulated object from depth data of a single sensor. To this end, we combine deformable mesh tracking, motion segmentation based on spectral clustering and skeletonization based on mean curvature flow. The fully rigged model then consists of a watertight mesh, embedded skeleton, and skinning weights.
منابع مشابه
Capturing Hand-Object Interaction and Reconstruction of Manipulated Objects
by Dimitrios Tzionas for the degree of Doctor rerum naturalium Hand motion capture with an RGB-D sensor gained recently a lot of research attention, however, even most recent approaches focus on the case of a single isolated hand. We focus instead on hands that interact with other hands or with a rigid or articulated object. Our framework successfully captures motion in such scenarios by combin...
متن کاملReal-Time Image Pickup System for Multiview Volumetric 3D Display Using RGB-D Camera
The present paper proposes an image pickup system for coarse integral volumetric imaging (CIVI), which is a 3D display solution combining multiview technology based on integral imaging and volumetric imaging technology using multilayered panels. In order to apply CIVI display system for live action videos, an image pickup system that can obtain not only multiview image but also depth informatio...
متن کاملQuality Enhancement of 3D Models Reconstructed By RGB-D Camera Systems
QUALITY ENHANCEMENT OF 3D MODELS RECONSTRUCTED BY RGB-D CAMERA SYSTEMS by Chuanbo Wang The University of Wisconsin-Milwaukee, 2015 Under the Supervision of Professor Zeyun Yu Low-cost RGB-D cameras like Microsoft's Kinect capture RGB data for each vertex while reconstructing 3D models from objects with obvious drawbacks of poor mesh and texture qualities due to their hardware limitations. I...
متن کاملHand Gesture Recognition from RGB-D Data using 2D and 3D Convolutional Neural Networks: a comparative study
Despite considerable enhances in recognizing hand gestures from still images, there are still many challenges in the classification of hand gestures in videos. The latter comes with more challenges, including higher computational complexity and arduous task of representing temporal features. Hand movement dynamics, represented by temporal features, have to be extracted by analyzing the total fr...
متن کاملLearning Human Pose Models from Synthesized Data for Robust RGB-D Action Recognition
We propose Human Pose Models that represent RGB and depth images of human poses independent of clothing textures, backgrounds, lighting conditions, body shapes and camera viewpoints. Learning such universal models requires training images where all factors are varied for every human pose. Capturing such data is prohibitively expensive. Therefore, we develop a framework for synthesizing the trai...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
عنوان ژورنال:
دوره شماره
صفحات -
تاریخ انتشار 2016