Mingsong Dou

Fusion4D: real-time performance capture of challenging scenes

We contribute a new pipeline for live multi-view performance capture, generating temporally coherent high-quality reconstructions in real-time. Our algorithm supports both incremental reconstruction, improving the surface estimation over time, as well as parameterizing the nonrigid scene motion. Our approach is highly robust to both large frame-to-frame motion and topology changes, allowing us to reconstruct extremely challenging scenes. We demonstrate advantages over related real-time techniques that either deform an online generated template or continually fuse depth data nonrigidly into a single reference model. Finally, we show geometric reconstruction results on par with offline methods which require orders of magnitude more processing time and many more RGBD cameras.

3D scanning deformable objects with a single RGBD sensor

We present a 3D scanning system for deformable objects that uses only a single Kinect sensor. Our work allows considerable amount of nonrigid deformations during scanning, and achieves high quality results without heavily constraining user or camera motion. We do not rely on any prior shape knowledge, enabling general object scanning with freeform deformations. To deal with the drift problem when nonrigidly aligning the input sequence, we automatically detect loop closures, distribute the alignment error over the loop, and finally use a bundle adjustment algorithm to optimize for the latent 3D shape and nonrigid deformation parameters simultaneously. We demonstrate high quality scanning results in some challenging sequences, comparing with state of art nonrigid techniques, as well as ground truth data.

Holoportation: Virtual 3D Teleportation in Real-time

We present an end-to-end system for augmented and virtual reality telepresence, called Holoportation. Our system demonstrates high-quality, real-time 3D reconstructions of an entire space, including people, furniture and objects, using a set of new depth cameras. These 3D models can also be transmitted in real-time to remote users. This allows users wearing virtual or augmented reality displays to see, hear and interact with remote participants in 3D, almost as if they were present in the same physical space. From an audio-visual perspective, communicating and interacting with remote users edges closer to face-to-face communication. This paper describes the Holoportation technical system in full, its key interactive capabilities, the application scenarios it enables, and an initial qualitative study of using this new communication medium.

Scanning and tracking dynamic objects with commodity depth cameras

The 3D data collected using state-of-the-art algorithms often suffers from various problems, such as incompletion and inaccuracy. Using temporal information has been proven effective for improving the reconstruction quality; for example, KinectFusion [21] shows significant improvements for static scenes. In this work, we present a system that uses commodity depth and color cameras, such as Microsoft Kinects, to fuse the 3D data captured over time for dynamic objects to build a complete and accurate model, and then tracks the model to match later observations. The key ingredients of our system include a nonrigid matching algorithm that aligns 3D observations of dynamic objects by using both geometry and texture measurements, and a volumetric fusion algorithm that fuses noisy 3D data. We demonstrate that the quality of the model improves dramatically by fusing a sequence of noisy and incomplete depth data of human and that by deforming this fused model to later observations, noise-and-hole-free 3D models are generated for the human moving freely.

Exploring high-level plane primitives for indoor 3d reconstruction with a hand-held RGB-D camera

Given a hand-held RGB-D camera (e.g. Kinect), methods such as Structure from Motion (SfM) and Iterative Closest Point (ICP), perform poorly when reconstructing indoor scenes with few image features or little geometric structure information. In this paper, we propose to extract high level primitives---planes---from an RGB-D camera, in addition to low level image features (e.g. SIFT), to better constrain the problem and help improve indoor 3D reconstruction. Our work has two major contributions: first, for frame to frame matching, we propose a new scheme which takes into account both low-level appearance feature correspondences in RGB image and high-level plane correspondences in depth image. Second, in the global bundle adjustment step, we formulate a novel error measurement that not only takes into account the traditional 3D point re-projection errors, but also the planar surface alignment errors. We demonstrate with real datasets that our method with plane constraints achieves more accurate and more appealing results comparing with other state-of-the-art scene reconstruction algorithms in aforementioned challenging indoor scenarios.

General-purpose telepresence with head-worn optical see-through displays and projector-based lighting

In this paper we propose a general-purpose telepresence system design that can be adapted to a wide range of scenarios and present a framework for a proof-of-concept prototype. The prototype system allows users to see remote participants and their surroundings merged into the local environment through the use of an optical see-through head-worn display. Real-time 3D acquisition and head tracking allows the remote imagery to be seen from the correct point of view and with proper occlusion. A projector-based lighting control system permits the remote imagery to appear bright and opaque even in a lit room. Immersion can be adjusted across the VR continuum. Our approach relies only on commodity hardware; we also experiment with wider field of view custom displays.

Room-sized informal telepresence system

We present a room-sized telepresence system for informal gatherings rather than conventional meetings. Unlike conventional systems which constrain participants to sit in fixed positions, our system aims to facilitate casual conversations between people in two sites. The system consists of a wall of large flat displays at each of the two sites, showing a panorama of the remote scene, constructed from a multiplicity of color and depth cameras. The main contribution of this paper is a solution that ameliorates the eye contact problem during conversation in typical scenarios while still maintaining a consistent view of the entire room for all participants. We achieve this by using two sets of cameras - a cluster of ”Panorama Cameras” located at the center of the display wall and are used to capture a panoramic view of the entire room, and a set of ”Personal Cameras” distributed along the display wall to capture front views of nearby participants. A robust segmentation algorithm with the assistance of depth cameras and an image synthesis algorithm work together to generate a consistent view of the entire scene. In our experience this new approach generates fewer distracting artifacts than conventional 3D reconstruction methods, while effectively correcting for eye gaze.

Motion2fusion: real-time volumetric performance capture

We present Motion2Fusion, a state-of-the-art 360 performance capture system that enables *real-time* reconstruction of arbitrary non-rigid scenes. We provide three major contributions over prior work: 1) a new non-rigid fusion pipeline allowing for far more faithful reconstruction of high frequency geometric details, avoiding the over-smoothing and visual artifacts observed previously. 2) a high speed pipeline coupled with a machine learning technique for 3D correspondence field estimation reducing tracking errors and artifacts that are attributed to fast motions. 3) a backward and forward non-rigid alignment strategy that more robustly deals with topology changes but is still free from scene priors. Our novel performance capture system demonstrates real-time results nearing 3x speed-up from previous state-of-the-art work on the exact same GPU hardware. Extensive quantitative and qualitative comparisons show more precise geometric and texturing results with less artifacts due to fast motions or topology changes than prior art.

Immersive Learning Experiences for Surgical Procedures.

This paper introduces a computer-based system that is designed to record a surgical procedure with multiple depth cameras and reconstruct in three dimensions the dynamic geometry of the actions and events that occur during the procedure. The resulting 3D-plus-time data takes the form of dynamic, textured geometry and can be immersively examined at a later time; equipped with a Virtual Reality headset such as Oculus Rift DK2, a user can walk around the reconstruction of the procedure room while controlling playback of the recorded surgical procedure with simple VCR-like controls (play, pause, rewind, fast forward). The reconstruction can be annotated in space and time to provide more information of the scene to users. We expect such a system to be useful in applications such as training of medical students and nurses.

Enhancement of 3D Capture of Room-Sized Dynamic Scenes with Pan-Tilt-Zoom Cameras

We present a method for augmenting the 3D reconstruction of a dynamic indoor scene using Pan-Tilt-Zoom cameras. The system combines Pan-Tilt-Zoom cameras with static wide field-of-view depth cameras within a networked platform. Traditionally, Pan-Tilt-Zoom cameras have been extensively used in surveillance applications, since their ability to pan, tilt and zoom in on an object allows them to cover a large area with a reduced number of cameras. However, most of the existing work with PTZ cameras deals with scanning or tracking objects in large outdoor environments, where objects are typically large distances away from the cameras. We use PTZ cameras in an indoor setting to zoom in on relevant and interesting objects to get fine visual details. The fine details and high resolution imagery enables us to augment and refine the room’s 3D surface as constructed from off-the-shelf depth cameras statically mounted around the room. We show significant improvements in both texture quality and geometry when high-resolution imagery from multiple PTZ cameras is used to supplement the 3D model built from fixed commodity depth cameras.