... A preliminary evaluation shows that our technique is more effective than a direct adaption of... more ... A preliminary evaluation shows that our technique is more effective than a direct adaption of standard transformation widgets to the tactile paradigm. ... Figure 8: Trial performance mean and standard deviation for different user interfaces. ...
IEEE Transactions on Geoscience and Remote Sensing, 2000
... model is novel in that it contains both discrete and continuous hidden random variables; this... more ... model is novel in that it contains both discrete and continuous hidden random variables; this is why we call it a “hybrid” CRF. ... Once the model has been trained, we can use it to estimate theground surface (the hidden continuous variables) from the LiDAR data (the observed ...
Recent shape editing techniques, especially for man-made models, have gradually shifted focus fro... more Recent shape editing techniques, especially for man-made models, have gradually shifted focus from maintaining local, low-level geometric features to preserving structural, high-level characteristics like symmetry and parallelism. Such new editing goals typically require a ...
... A preliminary evaluation shows that our technique is more effective than a direct adaption of... more ... A preliminary evaluation shows that our technique is more effective than a direct adaption of standard transformation widgets to the tactile paradigm. ... Figure 8: Trial performance mean and standard deviation for different user interfaces. ...
Abstract The presence of characteristic fine folds is important for modeling realistic looking vi... more Abstract The presence of characteristic fine folds is important for modeling realistic looking virtual garments. While recent garment capture techniques are quite successful at capturing the low-frequency garment shape and motion over time, they often fail to capture the numerous high-frequency folds, reducing the realism of the reconstructed space-time models. In our work we propose a method for reintroducing fine folds into the captured models using data-driven dynamic wrinkling. We first estimate the shape and position of ...
1.Introduction Differential coordinates are essentially vectors encoded in the global coordinate ... more 1.Introduction Differential coordinates are essentially vectors encoded in the global coordinate system. Since the local features on a mesh are deformed and rotated during editing, the differ-ential coordinates must somehow be transformed to match the desired new orientations, otherwise distortion like shear-ing and stretching will occur. This transformation problem is basically a chicken-and-egg problem: the reconstruction of the deformed surface requires properly oriented differ-ential coordinates, while the reorientation of these coordi-nates depend on the unknown deformed mesh. We present an iterative Laplacian-based editing framework to solve this transformation problem. The only user input required are the positions of the handles, not their local frames. Thus our sys-tem supports simple point handle editing. Our iterative up-dating process nds the best orientations of local features, including the orientations at the point handles. 2.Laplacian Editing Let V = (v<SUB>1, v<SUB>2,..., vn) be the mesh vertex positions, and i be the index set of vertices adjacent to v i. The Laplacian Coordinate (LC) of a vertex v i is l i = &#229 <SUB>j2i w i j (v <SUB>j v<SUB>i), where w i j is the weight of the edge (i; j) corresponding to vertex v i. In matrix form, it is l = LV, where L is an n n matrix with elements derived from w i j. We refer to these ele-ments as the Laplacian coef cients. The basic idea of Lapla-cian editing is to nd the positions V, of the deformed mesh,V0 LV, l,, constrained by the positions of some selected vertices as the handles of the model [S 04, L 04]. This is equivalent to solving a sparse linear system AV, = b in least squares sense. Thus V, can be solved from the normal equations A, AV, = A, b.
This paper challenges the difficult problem of automatic semantic correspondence between two give... more This paper challenges the difficult problem of automatic semantic correspondence between two given shapes which are semantically similar but possibly geometrically very different (eg, a dog and an elephant). We argue that the challenging part is the establishment of a ...
... A preliminary evaluation shows that our technique is more effective than a direct adaption of... more ... A preliminary evaluation shows that our technique is more effective than a direct adaption of standard transformation widgets to the tactile paradigm. ... Figure 8: Trial performance mean and standard deviation for different user interfaces. ...
IEEE Transactions on Geoscience and Remote Sensing, 2000
... model is novel in that it contains both discrete and continuous hidden random variables; this... more ... model is novel in that it contains both discrete and continuous hidden random variables; this is why we call it a “hybrid” CRF. ... Once the model has been trained, we can use it to estimate theground surface (the hidden continuous variables) from the LiDAR data (the observed ...
Recent shape editing techniques, especially for man-made models, have gradually shifted focus fro... more Recent shape editing techniques, especially for man-made models, have gradually shifted focus from maintaining local, low-level geometric features to preserving structural, high-level characteristics like symmetry and parallelism. Such new editing goals typically require a ...
... A preliminary evaluation shows that our technique is more effective than a direct adaption of... more ... A preliminary evaluation shows that our technique is more effective than a direct adaption of standard transformation widgets to the tactile paradigm. ... Figure 8: Trial performance mean and standard deviation for different user interfaces. ...
Abstract The presence of characteristic fine folds is important for modeling realistic looking vi... more Abstract The presence of characteristic fine folds is important for modeling realistic looking virtual garments. While recent garment capture techniques are quite successful at capturing the low-frequency garment shape and motion over time, they often fail to capture the numerous high-frequency folds, reducing the realism of the reconstructed space-time models. In our work we propose a method for reintroducing fine folds into the captured models using data-driven dynamic wrinkling. We first estimate the shape and position of ...
1.Introduction Differential coordinates are essentially vectors encoded in the global coordinate ... more 1.Introduction Differential coordinates are essentially vectors encoded in the global coordinate system. Since the local features on a mesh are deformed and rotated during editing, the differ-ential coordinates must somehow be transformed to match the desired new orientations, otherwise distortion like shear-ing and stretching will occur. This transformation problem is basically a chicken-and-egg problem: the reconstruction of the deformed surface requires properly oriented differ-ential coordinates, while the reorientation of these coordi-nates depend on the unknown deformed mesh. We present an iterative Laplacian-based editing framework to solve this transformation problem. The only user input required are the positions of the handles, not their local frames. Thus our sys-tem supports simple point handle editing. Our iterative up-dating process nds the best orientations of local features, including the orientations at the point handles. 2.Laplacian Editing Let V = (v<SUB>1, v<SUB>2,..., vn) be the mesh vertex positions, and i be the index set of vertices adjacent to v i. The Laplacian Coordinate (LC) of a vertex v i is l i = &#229 <SUB>j2i w i j (v <SUB>j v<SUB>i), where w i j is the weight of the edge (i; j) corresponding to vertex v i. In matrix form, it is l = LV, where L is an n n matrix with elements derived from w i j. We refer to these ele-ments as the Laplacian coef cients. The basic idea of Lapla-cian editing is to nd the positions V, of the deformed mesh,V0 LV, l,, constrained by the positions of some selected vertices as the handles of the model [S 04, L 04]. This is equivalent to solving a sparse linear system AV, = b in least squares sense. Thus V, can be solved from the normal equations A, AV, = A, b.
This paper challenges the difficult problem of automatic semantic correspondence between two give... more This paper challenges the difficult problem of automatic semantic correspondence between two given shapes which are semantically similar but possibly geometrically very different (eg, a dog and an elephant). We argue that the challenging part is the establishment of a ...
Uploads
Papers by Hongbo Fu