Approximate Symmetry Detection in Partial 3D Meshes

Sipiran, Ivan; Gregor, Robert J.; Schreck, Tobias

doi:10.1111/cgf.12481

Cited by 96 publications

(50 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This is a good demonstration of the robustness of our method. In contrast, the method proposed by Sipiran et al [SGS14], requires a preprocessing step, in order to eliminate the internal contact surfaces and produce a manifold mesh.…”

Section: Resultsmentioning

confidence: 99%

“…In Figure 10 we also provide a comparison with another symmetry-based completion method, proposed by Sipiran et al [SGS14]. This approach automatically detects and uses the highest scoring symmetry plane to complete the missing part of an object.…”

Section: Resultsmentioning

confidence: 99%

“…The algorithm was also shown to produce approximate completion in objects with non-rigid transformations. More recently, Sipiran et al [SGS14] proposed an algorithm to detect reflectional symmetries in objects with large missing geometry. The algorithm finds symmetric correspondences, which are subsequently used to produce candidate reflectional planes.…”

Section: Related Workmentioning

confidence: 99%

“…Completion of a partial wheel cap object with varying degrees of partiality and comparison with[SGS14]. r denotes the Hausdorff RMS distance from the ground truth.…”

mentioning

confidence: 99%

See 3 more Smart Citations

Object Completion usingk-Sparse Optimization

Mavridis

Sipiran

Andreadis

et al. 2015

Computer Graphics Forum

View full text Add to dashboard Cite

We present a new method for the completion of partial globally-symmetric 3D objects, based on the detection of partial and approximate symmetries in the incomplete input dataset. In our approach, symmetry detection is formulated as a constrained sparsity maximization problem, which is solved efficiently using a robust RANSACbased optimizer. The detected partial symmetries are then reused iteratively, in order to complete the missing parts of the object. A global error relaxation method minimizes the accumulated alignment errors and a nonrigid registration approach applies local deformations in order to properly handle approximate symmetry. Unlike previous approaches, our method does not rely on the computation of features, it uniformly handles translational, rotational and reflectional symmetries and can provide plausible object completion results, even on challenging cases, where more than half of the target object is missing. We demonstrate our algorithm in the completion of 3D scans with varying levels of partiality and we show the applicability of our approach in the repair and completion of heavily eroded or incomplete cultural heritage objects.

show abstract

Section: Resultsmentioning

confidence: 99%

Section: Resultsmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

“…Completion of a partial wheel cap object with varying degrees of partiality and comparison with[SGS14]. r denotes the Hausdorff RMS distance from the ground truth.…”

mentioning

confidence: 99%

See 2 more Smart Citations

Object Completion usingk-Sparse Optimization

Mavridis

Sipiran

Andreadis

et al. 2015

Computer Graphics Forum

View full text Add to dashboard Cite

show abstract

“…Geometry Completion Geometry completion has a long history in 3D processing, known for cleaning up broken single objects or incomplete scenes. Small holes can be filled by primitives fitting [31,19], smoothness minimization [37,56,17], or structures analysis [25,35,39]. These methods however seriously depend on prior knowledge.…”

Section: Related Workmentioning

confidence: 99%

Deep Reinforcement Learning of Volume-Guided Progressive View Inpainting for 3D Point Scene Completion From a Single Depth Image

Han

Cui

Zhang

et al. 2019

2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)

View full text Add to dashboard Cite

We present a deep reinforcement learning method of progressive view inpainting for 3D point scene completion under volume guidance, achieving high-quality scene reconstruction from only a single depth image with severe occlusion. Our approach is end-to-end, consisting of three modules: 3D scene volume reconstruction, 2D depth map inpainting, and multi-view selection for completion. Given a single depth image, our method first goes through the 3D volume branch to obtain a volumetric scene reconstruction as a guide to the next view inpainting step, which attempts to make up the missing information; the third step involves projecting the volume under the same view of the input, concatenating them to complete the current view depth, and integrating all depth into the point cloud. Since the occluded areas are unavailable, we resort to a deep Q-Network to glance around and pick the next best view for large hole completion progressively until a scene is adequately reconstructed while guaranteeing validity. All steps are learned jointly to achieve robust and consistent results. We perform qualitative and quantitative evaluations with extensive experiments on the SUNCG data, obtaining better results than the state of the art.

show abstract

Geometric Matching

Sipiran

Mavridis

Schreck

2018

The Encyclopedia of Archaeological Sciences

View full text Add to dashboard Cite

Geometric matching methods compute correspondences between shapes or parts thereof. Geometric matching considers the geometry of the objects, as opposed to other aspects like appearance, material properties, or semantic annotations. Two main techniques for geometric matching make use of geometry registration and geometric features, respectively. Geometric matching can be applied to two‐dimensional (2D) or three‐dimensional (3D) data, with this entry focusing on 3D data. Geometric matching enables many useful applications in archaeology, including reassembly, completion, correspondence analysis, and shape search.

show abstract

Approximate Symmetry Detection in Partial 3D Meshes

Abstract: Symmetry is a common characteristic in natural and

Cited by 96 publications

References 27 publications

Object Completion usingk-Sparse Optimization

Object Completion usingk-Sparse Optimization

Deep Reinforcement Learning of Volume-Guided Progressive View Inpainting for 3D Point Scene Completion From a Single Depth Image

Geometric Matching

Contact Info

Product

Resources

About