Geometry Model Retrieval

Although many retrieval methods have been proposed to facilitate searching and reuse of 3D geometry models, most of these methods can only handle exact match, i.e., the retrieved models need to be very similar in shape and pose to the input model. This can seriously affects the retrieval performance as these methods consider models of similar shape but different poses as different models.

In this project, we are developing geometry retrieval techniques that consider only the shape but not the pose of geometry models.

Publications:

Gary Tam and Rynson Lau, "Embedding Retrieval of Articulated Geometry Models," IEEE Trans. on Pattern Analysis and Machine Intelligence, 34(11):2134-2146, Nov. 2012.

Figure03

Due to the popularity of computer games and animation, research on 3D articulated geometry model retrieval is attracting a lot of attention in recent years. However, most existing works extract high dimensional features to represent models and suffer from practical limitations. First, misalignment in high dimensional features may produce unreliable Euclidean distances and affect retrieval accuracy. Second, the curse of dimensionality also degrades efficiency. In this paper, we propose an embedding retrieval framework to improve the practicability of these methods. It is based on a manifold learning technique, the Diffusion Map (DM). We project all pairwise distances onto a low dimensional space. This improves retrieval accuracy because inter-cluster distances are exaggerated. Then we adapt the Density-Weighted Nystrom extension and further propose a novel step to locally align the Nystrom embedding to the eigensolver embedding so as to reduce extension error and preserve retrieval accuracy. Finally, we propose a heuristic to handle disconnected manifolds by augmenting the kernel matrix with multiple similarity measures and shortcut edges, and further discuss the choice of DM parameters. We have incorporated two existing matching algorithms for testing. Our experimental results show improvement in precision at high recalls and in speed. Our work provides a robust retrieval framework for the matching of multimedia data that lie on manifolds. [bibtex] [matlab code]

Gary Tam and Rynson Lau, "Deformable Model Retrieval Based on Topological and Geometric Signatures," IEEE Trans. on Visualization and Computer Graphics, 13(3):470-482, May 2007.

icPR_dog_Dist1icPR_dog_Dist2

With the increasing popularity of 3D applications such as computer games, a lot of 3D geometry models are being created. To encourage sharing and reuse, techniques that support matching and retrieval of these models are emerging. However, only a few of them can handle deformable models, i.e., models of different poses, and these methods are generally very slow. In this paper, we present a novel method for efficient matching and retrieval of 3D deformable models. Our research idea stresses on using both topological and geometric features at the same time. First, we propose Topological Point Ring (TPR) analysis to locate reliable topological points and rings. Second, we capture both local and global geometric information to characterize each of these topological features. To compare the similarity of two models, we adapt the Earth Mover Distance (EMD) as the distance function, and construct an indexing tree to accelerate the retrieval process. We demonstrate the performance of the new method, both in terms of accuracy and speed, through a large number of experiments. [bibtex]

Gary Tam, Rynson Lau, and C.W. Ngo, "Deformable Geometry Model Matching by Topological and Geometric Signatures," Proc. ICPR, pp. 910-913, Aug. 2004.

2-way_5dino-pet_parted2-way_6

 

In this paper, we present a novel method for efficient 3D model comparison. The method matches highly deformed models by comparing topological and geometric features. First, we propose "Bi-directional LSD analysis" to locate reliable topological points and rings. Second, based on these points and rings, a set of bounded regions are extracted as topological features. Third, for each bounded region, we capture additional spatial location, curvature and area distribution as geometric data. Fourth, to model the topological importance of each bounded region, we capture its effective area as weight. By using "Earth Mover Distance" as a distance measure between two models, our method can achieve a high accuracy in our retrieval experiment, with precision of 0.53 even at recall rate of 1.0. [bibtex]

Gary Tam, Rynson Lau, and C.W. Ngo, "Deformable Geometry Model Matching Using Bipartite Graph," Proc. Computer Graphics International (CGI), pp. 335-342, June 2004. (Due to some error, the title of this paper in the proceedings was wrongly printed as "Deformable Object Model Matching by Topological and Geometric Similarity".)

adv_cat4adv_hipo4adv_epcot

adv_dogsadv_horse1adv_horse

In this paper, we present a novel method for efficient 3D model comparison. The method is designed to match highly deformed models through capturing two types of information. First, we propose a feature point extraction algorithm, which is based on "Level Set Diagram", to reliably capture the topological points of a general 3D model. These topological points represent the skeletal structure of the model. Second, we also capture both spatial and curvature information, which describes the global surface of a 3D model. This is different from traditional topological 3D matching methods that use only low-dimension local features. Our method can accurately distinguish different types of 3D models even if they have similar topology. By applying the bipartite graph matching technique, our method can achieve a high precision of 0.54 even at a recall rate of 1.0 as demonstrated in our experimental results. [bibtex]

Last updated in January, 2012.