This paper describes an automatic annotation, or autotagging, algorithm that attaches textual tags to 3D models based on their shape and semantic classes. The proposed method employs Manifold Ranking ...by Zhou et al, an algorithm that takes into account both local and global distributions of feature points, for tag relevance computation. Using Manifold Ranking, our method propagates multiple tags attached to a training subset of models in a database to the other tag-less models. After the relevance values for multiple tags are computed for tag-less points, the method selects, based on the distribution of feature points for each tag, the threshold at which the tag is selected or discarded for the points. Experimental evaluation of the method using a text-based 3D model retrieval setting showed that the proposed method is effective in autotagging 3D shape models.
Three-dimensional (3D) graphics is about to become a full-fledged multimedia data type, prompted by the increasing popularity of virtual reality modeling language (VRML)
15and imminent ...standardization of MPEG-4
16.
This paper presents several algorithms for embedding data in triangular meshes, arguably the most important component in both VRML and MPEG-4 in defining arbitrary shapes. A topology-modifying algorithm described in this paper embeds bit string in connectivity of triangles, while another algorithm cuts out patterns from a mesh. Yet another algorithm modifies texture coordinate, a non-geometrical quantity, for embedding.
Watermarks embedded in 3D graphics contents could be used as a tool in managing intellectual property and other issues associated with these contents.
In this paper, we propose and evaluate a novel object detection architecture called Cascaded Multi-Channel Feature Pyramid Network, or CM-FPN. The proposed network, which is based on Feature Pyramid ...Network by Lin et al., employs multi-stage cascaded top-down feature pyramid networks to extract more semantic multiresolution feature maps for object region proposal and object classification. Depths of the feature maps are adjusted so that the feature maps in the later stages of the cascades where they are more semantic have higher channel depths. Experimental evaluation of the proposed approach has shown that the proposed method produces higher object detection accuracy.
In this paper, we propose a method for shape-similarity search of 3D polygonal-mesh models. The system accepts triangular meshes, but tolerates degenerated polygons, disconnected component, and other ...anomalies. As the feature vector, the method uses a combination of three vectors, (1) the moment of inertia, (2) the average distance of surface from the axis, and (3) the variance of distance of the surface from the axis. Values in each vector are discretely parameterized along each of the three principal axes of inertia of the model. We employed the Euclidean distance and the elastic-matching distance as the measures of distance between pairs of feature vectors. Experiments showed that the proposed shape features and distance measures perform fairly well in retrieving models having similar shape from a database of VRML models.
The Local Depth-SIFT (LD-SIFT) algorithm by Darom, et al. 2 captures 3D geometrical features locally at interest points detected on a densely-sampled, manifold mesh representation of the 3D shape. ...The LD-SIFT has shown good retrieval accuracy for 3D models defined as densely sampled manifold mesh. However, it has two shortcomings. The LD-SIFT requires the input mesh to be densely and evenly sampled. Furthermore, the LD-SIFT can't handle 3D models defined as a set of multiple connected components or a polygon soup. This paper proposes two extensions to the LD-SIFT to alleviate these weaknesses. First extension shuns interest point detection, and employs dense sampling on the mesh. Second extension employs remeshing by dense sample points followed by interest point detection a la LD-SIFT Experiments using three different benchmark databases showed that the proposed algorithms significantly outperform the LD-SIFT in terms of retrieval accuracy.
This paper proposes an improvement to Manifold Ranking algorithm used for search results ranking in the context of shape-based 3D model retrieval. Manifold Ranking algorithm by Zhou et al estimates, ...given a set of high-dimensional feature vectors, a lower-dimensional manifold on which the features lie. It then computes diffusion-based distances from a feature vector (or feature vectors) to the other feature vectors on the manifold. When applied to content-based retrieval, overall retrieval accuracy is significantly better than a "simple" fixed distance metric. However, in a small neighborhood of query, retrieval ranks obtained by a "simple" distance metric (e.g., L1-norm) performs better than those obtained by Manifold Ranking. Proposed re-ranking algorithm tries to combine ranking results due to both simple distance metric and Manifold Ranking in an automatic query expansion framework for better ranking results. Experimental evaluation has shown that the proposed method is effective in improving retrieval accuracy.
This paper presents a shape-blending algorithm that interpolates between 2D and 3D polyhedrons. Shape blending, which is sometimes called shape metamorphosis or geometric morphing, has applications ...in such areas as entertainment and medical visualization. Our algorithm directly interpolates vertices of polyhedral source shapes by using variationally optimized subdivision surfaces. To interpolate a pair of 3D polyhedrons, for example, a smooth 4D tetrahedral interpolator subdivision surface is created. Intersecting the 4D subdivision surface with another 4D surface produces a blended 3D mesh. Variational optimization of the interpolator surface ensures a smooth shape transition. At the same time, manipulable nature of the interpolator subdivision surface allows for feature correspondences, shape transition effects, and other controls over the shape blending.