CuFusion: Accurate Real-Time Camera Tracking and Volumetric Scene Reconstruction with a Cuboid

Zhang, Chen; Hu, Yu

doi:10.3390/s17102260

Cited by 9 publications

(7 citation statements)

References 39 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…corners) to different corner-assisted modalities. In order to demonstrate the effect of super-resolved corners on ICP registration, we sample random scenes from the CuFusion bunny sequence [2] as well as Redwood Kiosk sequence [46] and run a pairwise registration. We plot the median of the relative pose error (RPE) against the downsampling factor for scans that are temporally about 0.33 and 0.1 seconds apart for CuFusion and Redwood sequences respectively.…”

Section: A Quantitative Results A) Detection Of Planes and Intersectmentioning

confidence: 99%

“…V. EXPERIMENTAL EVALUATION a) Datasets: In order to demonstrate the broad applicability of our proposed method, we evaluate our multi-purpose primitives on different datasets including SceneNN [44], ICL-NUIM [45], Cu3D [2] and Redwood [46]. It is noteworthy that for the task of primitive detection and discovery there are not many designated datasets.…”

Section: Refinement Of Orthogonality Primitivesmentioning

confidence: 99%

“…This work was partially supported by the ERC Consolidator Grant "3D Reloaded" and by Siemens AG. 1 Steps of our algorithm on CuFusion dataset [2]. We can simultaneously detect orthogonal planes and their intersection lines (b,c), compute the orthogonal relation graph and use it to extract reliable corners with 6D local reference frames (d).…”

Section: Introductionmentioning

confidence: 99%

“…Rotational and translational errors in corner assisted ICP on the CuFusion[2] and Redwood-Kiosk[46] datasets. (b) Before clustering / refinement (d) Final detections (a) Surface normals (c) Plane normals of detections Detection of orthogonality primitives on an ICL-NUIM scene.…”

mentioning

confidence: 99%

See 3 more Smart Citations

From Planes to Corners: Multi-Purpose Primitive Detection in Unorganized 3D Point Clouds

Sommer

Sun

Guibas

et al. 2020

IEEE Robot. Autom. Lett.

View full text Add to dashboard Cite

We propose a new method for segmentation-free joint estimation of orthogonal planes, their intersection lines, relationship graph and corners lying at the intersection of three orthogonal planes. Such unified scene exploration under orthogonality allows for multitudes of applications such as semantic plane detection or local and global scan alignment, which in turn can aid robot localization or grasping tasks. Our two-stage pipeline involves a rough yet joint estimation of orthogonal planes followed by a subsequent joint refinement of plane parameters respecting their orthogonality relations. We form a graph of these primitives, paving the way to the extraction of further reliable features: lines and corners. Our experiments demonstrate the validity of our approach in numerous scenarios from wall detection to 6D tracking, both on synthetic and real data.

show abstract

Section: A Quantitative Results A) Detection Of Planes and Intersectmentioning

confidence: 99%

Section: Refinement Of Orthogonality Primitivesmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

mentioning

confidence: 99%

See 2 more Smart Citations

From Planes to Corners: Multi-Purpose Primitive Detection in Unorganized 3D Point Clouds

Sommer

Sun

Guibas

et al. 2020

IEEE Robot. Autom. Lett.

View full text Add to dashboard Cite

show abstract

“…In the past few years, researchers have explored a number of online [ 5 , 6 , 7 , 8 , 9 , 10 ] and offline [ 11 , 12 , 13 , 14 , 15 , 16 ] approaches to address these issues: Kintinuous [ 6 ], ElasticFusion [ 9 ], InfiniTAMv3 [ 10 ] and BundleFusion [ 14 ] address accumulated tracking drift by detecting loop closures; Choi et al’s method [ 12 , 13 ] and 3DMatch [ 11 ] reconstruct local smooth scene fragments and globally align them together with 3D features to obtain high-quality 3D reconstruction; DVOSLAM [ 7 , 8 ] proposes a novel direct method by minimizing the photometric error, which outperforms the dense ICP-based method in terms of efficiency.…”

Section: Introductionmentioning

confidence: 99%

Robust and Efficient CPU-Based RGB-D Scene Reconstruction

Gao

et al. 2018

Sensors

View full text Add to dashboard Cite

3D scene reconstruction is an important topic in computer vision. A complete scene is reconstructed from views acquired along the camera trajectory, each view containing a small part of the scene. Tracking in textureless scenes is well known to be a Gordian knot of camera tracking, and how to obtain accurate 3D models quickly is a major challenge for existing systems. For the application of robotics, we propose a robust CPU-based approach to reconstruct indoor scenes efficiently with a consumer RGB-D camera. The proposed approach bridges feature-based camera tracking and volumetric-based data integration together and has a good reconstruction performance in terms of both robustness and efficiency. The key points in our approach include: (i) a robust and fast camera tracking method combining points and edges, which improves tracking stability in textureless scenes; (ii) an efficient data fusion strategy to select camera views and integrate RGB-D images on multiple scales, which enhances the efficiency of volumetric integration; (iii) a novel RGB-D scene reconstruction system, which can be quickly implemented on a standard CPU. Experimental results demonstrate that our approach reconstructs scenes with higher robustness and efficiency compared to state-of-the-art reconstruction systems.

show abstract

CuFusion2: Accurate and Denoised Volumetric 3D Object Reconstruction Using Depth Cameras

Zhang

2019

IEEE Access

View full text Add to dashboard Cite

The 3D object reconstruction from depth image streams using Kinect-style depth cameras has been extensively studied. In this paper, we propose an approach for accurate camera tracking and volumetric dense surface reconstruction, assuming that a known cuboid reference object is present in the scene. Our contribution is threefold. First, we maintain the drift-free camera pose tracking by incorporating the 3D geometric constraints of the cuboid reference object into the image registration process. Second, we reformulate the problem of depth stream fusion as a binary classification problem, enabling highfidelity surface reconstruction, especially in the concave zones of objects. Third, we further present a surface denoising strategy to mitigate the topological inconsistency (e.g., holes and dangling triangles), which facilitates the generation of a noise-free triangle mesh. We extend our public dataset CU3D with several new image sequences, test our algorithm on these sequences, and quantitatively compare them with other state-of-the-art algorithms. Both our dataset and our algorithm are available as open-source content at https://github.com/zhangxaochen/CuFusion for other researchers to reproduce and verify our results. INDEX TERMS 3D object reconstruction, depth cameras, Kinect sensors, open source, signal denoising, SLAM. CHEN ZHANG received the B.S. degree in computer science from Zhejiang University, China, in 2013, and the Ph.D. degree from the College of Computer Science and Technology, Zhejiang University, China. He is currently with the State Key Laboratory of CAD and CG, Computer Animation and Perception Group, Zhejiang University. His primary research interests include simultaneous localization and mapping (SLAM), and 3D reconstruction.

show abstract

CuFusion: Accurate Real-Time Camera Tracking and Volumetric Scene Reconstruction with a Cuboid

Cited by 9 publications

References 39 publications

From Planes to Corners: Multi-Purpose Primitive Detection in Unorganized 3D Point Clouds

From Planes to Corners: Multi-Purpose Primitive Detection in Unorganized 3D Point Clouds

Robust and Efficient CPU-Based RGB-D Scene Reconstruction

CuFusion2: Accurate and Denoised Volumetric 3D Object Reconstruction Using Depth Cameras

Contact Info

Product

Resources

About