Non‐Rigid Registration Under Isometric Deformations

Huang, Qixing; Adams, Bart; Wicke, Martin; Guibas, Leonidas J.

doi:10.1111/j.1467-8659.2008.01285.x

Cited by 237 publications

(315 citation statements)

References 42 publications

(55 reference statements)

Supporting

Mentioning

306

Contrasting

Order By: Relevance

“…When canonical forms are aligned directly, there is no guarantee that close-by points in one shape match close-by points in the other shape. Huang et al [18] proceed by iteratively alternating between a correspondence optimization and a deformation optimization. The approach can be viewed as an extension of the Iterative Closest Point algorithm (ICP) [8] that is often used to solve the rigid correspondence problem.…”

Section: Related Workmentioning

confidence: 99%

“…To improve the efficiency of the algorithm, the tree of all matching features is pruned if the features are too dissimilar. Nonetheless, the algorithm is not as efficient as the algorithm of Huang et al [18]. Once the feature correspondences are computed, the full correspondence is found by deforming the full mesh based on the feature points.…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Landmark-free posture invariant human shape correspondence

Wuhrer

Shu

2011

Vis Comput

View full text Add to dashboard Cite

We consider the problem of computing accurate point-to-point correspondences among a set of human bodies in varying postures using a landmark-free approach. The approach learns the locations of the anthropometric landmarks present in a database of human models in strongly varying postures and uses this knowledge to automatically predict the locations of these anthropometric landmarks on a newly available scan. The predicted landmarks are then used to compute point-to-point correspondences between a rigged template model and the newly available scan.

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

Landmark-free posture invariant human shape correspondence

Wuhrer

Shu

2011

Vis Comput

View full text Add to dashboard Cite

show abstract

“…Huang et al [18] proceeds by iteratively alternating between a correspondence optimization and a deformation optimization. The approach can be viewed as an extension of the Iterative Closest Point algorithm (ICP) [8] that is often used to solve the rigid correspondence problem.…”

Section: Related Workmentioning

confidence: 99%

“…Computing the correspondence among a set of human shapes is further complicated by the intrinsic symmetry of the human body shape and by the shape variation across a population. Hence, fully-automatic correspondence methods that exploit the intrinsic geometry of the shape [18,33] may fail when corresponding humans that differ in shape.…”

Section: Introductionmentioning

confidence: 99%

“…To the best of our knowledge, previous methods for analyzing the human body shape use known landmark positions when computing the correspondences. Furthermore, methods that compute correspondences for arbitrary shapes in a fully automatic manner [18,33] take advantage of the intrinsic geometry of the shapes and may fail for human shapes due to intrinsic symmetries. We review previous methods in detail in Section 2.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Human shape correspondence with automatically predicted landmarks

Wuhrer

Shu

2011

Machine Vision and Applications

View full text Add to dashboard Cite

We consider the problem of computing accurate point-to-point correspondences among a set of human bodies in similar posture using a landmark-free approach. The approach learns the locations of the anthropometric landmarks present in a database of human models in similar postures and uses this knowledge to automatically predict the locations of these anthropometric landmarks on a newly available scan. The predicted landmarks are then used to compute point-to-point correspondences between a template model and the newly available scan. This study conducts a largescale evaluation to examine the accuracy of the computed correspondences. Furthermore, we show that the correspondences are accurate enough for the application of motion transfer.

show abstract

Human body reconstruction from limited number of points

Taştan

Sahillioğlu

2021

Computer Animation & Virtual

View full text Add to dashboard Cite

We propose a novel approach for reconstructing plausible three-dimensional (3D) human body models from small number of 3D points which represent body parts. We leverage a database of 3D models of humans varying from each other by physical attributes such as age, gender, weight, and height. First we divide the bodies in database into seven semantic regions. Then, for each input region consisting of maximum 40 points, we search the database for the best matching body part. For the matching criterion, we use the distance between novel point-based features of input points and body parts in the database. We then combine the matched parts from different bodies into one body, with the help of Laplacian deformation, which results in a plausible human body. To evaluate our results objectively, we pick points from each part of the ground-truth human body models, then reconstruct them using our method and compare the resulting bodies with the corresponding ground-truths. Also, our results are compared with registration-based results. In addition, we run our algorithm with noisy data to test the robustness of our method and run it with input points whose body parts are manually edited, which produces plausible human bodies that do not even exist in our database. Our experiments verify qualitatively and quantitatively that the proposed approach reconstructs human bodies with different physical attributes from a small number of points using a small database.

show abstract

Non‐Rigid Registration Under Isometric Deformations

Abstract: Abstract

Cited by 237 publications

References 42 publications

Landmark-free posture invariant human shape correspondence

Landmark-free posture invariant human shape correspondence

Human shape correspondence with automatically predicted landmarks

Human body reconstruction from limited number of points

Contact Info

Product

Resources

About