Elastic Fragments for Dense Scene Reconstruction

Zhou, Qian-Yi; Miller, Stephen D.; Koltun, Vladlen

doi:10.1109/iccv.2013.65

Cited by 90 publications

(57 citation statements)

References 34 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…But the approach is in a strictly offline framework. Similar to work also done by Zhou et al, 18 the approach tries to deal with both noise error and camera distortion. The approach achieves high fidelity reconstruction by generating 3-D models of local fragments first, and then deforming the local fragments to align with each other.…”

Section: Related Workmentioning

confidence: 68%

Real-time depth camera tracking with geometrically stable weight algorithm

Feng

Wang

2017

Opt. Eng

View full text Add to dashboard Cite

Abstract. We present an approach for real-time camera tracking with depth stream. Existing methods are prone to drift in sceneries without sufficient geometric information. First, we propose a new weight method for an iterative closest point algorithm commonly used in real-time dense mapping and tracking systems. By detecting uncertainty in pose and increasing weight of points that constrain unstable transformations, our system achieves accurate and robust trajectory estimation results. Our pipeline can be fully parallelized with GPU and incorporated into the current real-time depth camera tracking system seamlessly. Second, we compare the state-of-theart weight algorithms and propose a weight degradation algorithm according to the measurement characteristics of a consumer depth camera. Third, we use Nvidia Kepler Shuffle instructions during warp and block reduction to improve the efficiency of our system. Results on the public TUM RGB-D database benchmark demonstrate that our camera tracking system achieves state-of-the-art results both in accuracy and efficiency.

show abstract

Section: Related Workmentioning

confidence: 68%

Real-time depth camera tracking with geometrically stable weight algorithm

Feng

Wang

2017

Opt. Eng

View full text Add to dashboard Cite

show abstract

“…This is in contrast to other dense reconstruction systems which don't strictly perform both tracking and mapping in real-time [18,19]. The approach we have developed in this paper is closer to the offline dense scene reconstruction system of Zhou et al than a traditional SLAM system in how it places much more emphasis on the accuracy of the reconstructed map over the estimated trajectory [27].…”

Section: Introductionmentioning

confidence: 69%

Robotics: Science and Systems XI

2015

View full text Add to dashboard Cite

Abstract-We present a novel approach to real-time dense visual SLAM. Our system is capable of capturing comprehensive dense globally consistent surfel-based maps of room scale environments explored using an RGB-D camera in an incremental online fashion, without pose graph optimisation or any postprocessing steps. This is accomplished by using dense frame-tomodel camera tracking and windowed surfel-based fusion coupled with frequent model refinement through non-rigid surface deformations. Our approach applies local model-to-model surface loop closure optimisations as often as possible to stay close to the mode of the map distribution, while utilising global loop closure to recover from arbitrary drift and maintain global consistency.

show abstract

“…Zhou and Koltun [24] proposed an impressive offline 3D reconstruction method which focuses on preserving details of points of interest with high density values across RGB-D frames, and runs pose graph optimization to obtain globally consistent pose estimations for these points. Two other works by Zhou et al [25] and Choi et al [26] both detect smooth fragments as point of interest zones and attempt to maximize the consistency of corresponding points in fragments across frames using global optimization.…”

Section: Offline Rgb-d Reconstructionmentioning

confidence: 99%

Feature-based RGB-D camera pose optimization for real-time 3D reconstruction

Wang

Guo

2017

Comp. Visual Media

View full text Add to dashboard Cite

In this paper we present a novel featurebased RGB-D camera pose optimization algorithm for real-time 3D reconstruction systems. During camera pose estimation, current methods in online systems suffer from fast-scanned RGB-D data, or generate inaccurate relative transformations between consecutive frames. Our approach improves current methods by utilizing matched features across all frames and is robust for RGB-D data with large shifts in consecutive frames.We directly estimate camera pose for each frame by efficiently solving a quadratic minimization problem to maximize the consistency of 3D points in global space across frames corresponding to matched feature points. We have implemented our method within two state-of-the-art online 3D reconstruction platforms. Experimental results testify that our method is efficient and reliable in estimating camera poses for RGB-D data with large shifts.

show abstract

Elastic Fragments for Dense Scene Reconstruction

Cited by 90 publications

References 34 publications

Real-time depth camera tracking with geometrically stable weight algorithm

Real-time depth camera tracking with geometrically stable weight algorithm

Robotics: Science and Systems XI

Feature-based RGB-D camera pose optimization for real-time 3D reconstruction

Contact Info

Product

Resources

About