3D self-portraits

Abstract

3D scanning pose change output reconstruction textured reconstruction large variety of examples 3D print Figure 1: With our system, users can scan themselves with a single 3D sensor by rotating the same pose for a few different views (typically eight, ⇠45 degrees apart) to cover the full body. Our method robustly registers and merges different scans into a watertight surface with consistent texture in spite of shape changes during repositioning, and lighting differences between the scans. These surfaces are suitable for applications such as online avatars or 3D printing (the miniature shown here was printed using a ZPrinter 650.) AbstractWe develop an automatic pipeline that allows ordinary users to capture complete and fully textured 3D models of themselves in minutes, using only a single Kinect sensor, in the uncontrolled lighting environment of their own home. Our method requires neither a turntable nor a second operator, and is robust to the small deformations and changes of pose that inevitably arise during scanning. After the users rotate themselves with the same pose for a few scans from different views, our system stitches together the captured scans using multi-view non-rigid registration, and produces watertight final models. To ensure consistent texturing, we recover the underlying albedo from each scanned texture and generate seamless global textures using Poisson blending. Despite the minimal requirements we place on the hardware and users, our method is suitable for full body capture of challenging scenes that cannot be handled well using previous methods, such as those involving loose clothing, complex poses, and props.

Real-Time Enhancement of Dynamic Depth Videos with Non-Rigid Deformations

“…Since these methods and their immediate derivatives, the real challenge that the research community has been facing is extending the multi-frame depth enhancement concept to scenes with non-rigid deformations. There have been few attempts to handle single object scanning under relative small non-rigidities by replacing a global rigid registration with a non-rigid alignment [37], [38], [39]. These techniques, however, cannot handle large deformations, and are not very practical for real-time applications.…”

A Linear Approach for Depth and Colour Camera Calibration Using Hybrid Parameters

“…For instance, reconstruction algorithms [20][21] need the intrinsic parameters of depth camera to compute coordinates of 3D points. Therefore we introduce a scheme to compute explicit parameters with hybrid parameter matrix.…”

3D scanning deformable objects with a single RGBD sensor

“…[24,11,18]); 2) require multiple cameras (e.g. [5]); 3) capture a static pre-scan as template prior (e.g.…”

“…Many follow-up systems based on KinectFusion have specifically looked at scanning humans (e.g., for 3D printing or generating avatars) where the user rotates in front of the Kinect while maintaining a roughly rigid pose, e.g., [24,11,18,27,7]. This highlights the fundamental issue when scanning living things -they ultimately move.…”

“…We wish to avoid such scene assumptions. Li et al [11] adapt a more general nonrigid registration framework which can support a wider range of poses, clothing or even multiple users. This system demonstrates compelling results but relies on a very specific type of user interaction: the user moves in roughly 45 degree increments, in front of Kinect, and at each step remains static, whilst the motorized sensor scans up and down.…”