The semantic segmentation of underwater imagery is an important step in the ecological analysis o... more The semantic segmentation of underwater imagery is an important step in the ecological analysis of coral habitats. To date, scientists produce fine-scale area annotations manually, an exceptionally time-consuming task that could be efficiently automatized by modern CNNs. This paper extends our previous work presented at the 3DUW’19 conference, outlining the workflow for the automated annotation of imagery from the first step of dataset preparation, to the last step of prediction reassembly. In particular, we propose an ecologically inspired strategy for an efficient dataset partition, an over-sampling methodology targeted on ortho-imagery, and a score fusion strategy. We also investigate the use of different loss functions in the optimization of a Deeplab V3+ model, to mitigate the class-imbalance problem and improve prediction accuracy on coral instance boundaries. The experimental results demonstrate the effectiveness of the ecologically inspired split in improving model performan...
We present a new algorithm for the semi-regular quadrangulation of an input surface, driven by it... more We present a new algorithm for the semi-regular quadrangulation of an input surface, driven by its line features, such as sharp creases. We define a perfectly feature-aligned cross-field and a coarse layout of polygonal-shaped patches where we strictly ensure that all the feature-lines are represented as patch boundaries. To be able to consistently do so, we allow non-quadrilateral patches and T-junctions in the layout; the key is the ability to constrain the layout so that it still admits a globally consistent, T-junction-free, and pure-quad internal tessellation of its patches. This requires the insertion of additional irregular-vertices inside patches, but the regularity of the final-mesh is safeguarded by optimizing for both their number and for their reciprocal alignment. In total, our method guarantees the reproduction of feature-lines by construction, while still producing good quality, isometric, pure-quad, conforming meshes, making it an ideal candidate for CAD models. More...
The paper deals with the parallelization of Delaunay triangulation algorithms, giving more emphas... more The paper deals with the parallelization of Delaunay triangulation algorithms, giving more emphasis to pratical issues and implementation than to theoretical complexity. Two parallel implementations are pre- sented. The first one is built on DeWall, an Ed triangulator based on an original interpretation of the divide & conquer paradigm. The second is based on an incremental construction algorithm. The paral-
We present a simple technique to improve the perception of an object's shape. Bump mapping i... more We present a simple technique to improve the perception of an object's shape. Bump mapping is well known in the computer graphics community for providing the impression of small-scale geometrical features, which are not explicitly modelled. Here, we propose a similar approach (variation of normals) for the purpose of enhancing the perception of a given geometry. Our approach is based on a simple modification of the surface normals in order to enhance the geometric features of the object during the rendering. The enhanced normals produced by this approach can be used in any rendering technique. The technique presented is particularly well suited to improve the rendering of mechanical parts where common straightforward shading techniques can often generate shading ambiguities. r 2004 Elsevier Ltd. All rights reserved.
The semantic segmentation of underwater imagery is an important step in the ecological analysis o... more The semantic segmentation of underwater imagery is an important step in the ecological analysis of coral habitats. To date, scientists produce fine-scale area annotations manually, an exceptionally time-consuming task that could be efficiently automatized by modern CNNs. This paper extends our previous work presented at the 3DUW’19 conference, outlining the workflow for the automated annotation of imagery from the first step of dataset preparation, to the last step of prediction reassembly. In particular, we propose an ecologically inspired strategy for an efficient dataset partition, an over-sampling methodology targeted on ortho-imagery, and a score fusion strategy. We also investigate the use of different loss functions in the optimization of a Deeplab V3+ model, to mitigate the class-imbalance problem and improve prediction accuracy on coral instance boundaries. The experimental results demonstrate the effectiveness of the ecologically inspired split in improving model performan...
We present a new algorithm for the semi-regular quadrangulation of an input surface, driven by it... more We present a new algorithm for the semi-regular quadrangulation of an input surface, driven by its line features, such as sharp creases. We define a perfectly feature-aligned cross-field and a coarse layout of polygonal-shaped patches where we strictly ensure that all the feature-lines are represented as patch boundaries. To be able to consistently do so, we allow non-quadrilateral patches and T-junctions in the layout; the key is the ability to constrain the layout so that it still admits a globally consistent, T-junction-free, and pure-quad internal tessellation of its patches. This requires the insertion of additional irregular-vertices inside patches, but the regularity of the final-mesh is safeguarded by optimizing for both their number and for their reciprocal alignment. In total, our method guarantees the reproduction of feature-lines by construction, while still producing good quality, isometric, pure-quad, conforming meshes, making it an ideal candidate for CAD models. More...
The paper deals with the parallelization of Delaunay triangulation algorithms, giving more emphas... more The paper deals with the parallelization of Delaunay triangulation algorithms, giving more emphasis to pratical issues and implementation than to theoretical complexity. Two parallel implementations are pre- sented. The first one is built on DeWall, an Ed triangulator based on an original interpretation of the divide & conquer paradigm. The second is based on an incremental construction algorithm. The paral-
We present a simple technique to improve the perception of an object's shape. Bump mapping i... more We present a simple technique to improve the perception of an object's shape. Bump mapping is well known in the computer graphics community for providing the impression of small-scale geometrical features, which are not explicitly modelled. Here, we propose a similar approach (variation of normals) for the purpose of enhancing the perception of a given geometry. Our approach is based on a simple modification of the surface normals in order to enhance the geometric features of the object during the rendering. The enhanced normals produced by this approach can be used in any rendering technique. The technique presented is particularly well suited to improve the rendering of mechanical parts where common straightforward shading techniques can often generate shading ambiguities. r 2004 Elsevier Ltd. All rights reserved.
Uploads
Papers by Paolo Cignoni