The generation of high-quality 3D models from single 2D images remains challenging in terms of accuracy and completeness.Deep learning has emerged as a promising solution,offering new avenues for improvements.However,...The generation of high-quality 3D models from single 2D images remains challenging in terms of accuracy and completeness.Deep learning has emerged as a promising solution,offering new avenues for improvements.However,building models from scratch is computationally expensive and requires large datasets.This paper presents a transfer-learning-based approach for category-specific 3D reconstruction from a single 2D image.The core idea is to fine-tune a pre-trained model on specific object categories using new,unseen data,resulting in specialized versions of the model that are better adapted to reconstruct particular objects.The proposed approach utilizes a three-phase pipeline comprising image acquisition,3D reconstruction,and refinement.After ensuring the quality of the input image,a ResNet50 model is used for object recognition,directing the image to the corresponding category-specific model to generate a voxel-based representation.The voxel-based 3D model is then refined by transforming it into a detailed triangular mesh representation using the Marching Cubes algorithm and Laplacian smoothing.An experimental study,using the Pix2Vox model and the Pascal3D dataset,has been conducted to evaluate and validate the effectiveness of the proposed approach.Results demonstrate that category-specific fine-tuning of Pix2Vox significantly outperforms both the original model and the general model fine-tuned for all object categories,with substantial gains in Intersection over Union(IoU)scores.Visual assessments confirm improvements in geometric detail and surface realism.These findings indicate that combining transfer learning with category-specific fine tuning and refinement strategy of our approach leads to better-quality 3D model generation.展开更多
UML 2.0 activity diagrams (ADs) are largely used as a modeling language for flow-oriented behaviors in software and business processes. Unfortunately, their place/transition operational semantics is unable to capture ...UML 2.0 activity diagrams (ADs) are largely used as a modeling language for flow-oriented behaviors in software and business processes. Unfortunately, their place/transition operational semantics is unable to capture and preserve semantics of the newly defined high-level activities constructs such as Interruptible Activity Region. Particularly, basic Petri nets do not preserve the non-locality semantics and reactivity concept of ADs. This is mainly due to the absence of global synchronization mechanisms in basic Petri nets. Zero-safe nets are a high-level variant of Petri nets that ensure transitions global coordination thanks to a new kind of places, called zero places. Indeed, zero-safe nets naturally address Interruptible Activity Region that needs a special semantics, forcing the control flow by external events and defining a certain priority level of executions. Therefore, zero-safe nets are adopted in this work as semantic framework for UML 2.0 activity diagrams.展开更多
In the proposal, a construction project memory process based on the semantic annotation is presented. A project Mem-ory concerns the representation and the identification of the experience acquired during projects rea...In the proposal, a construction project memory process based on the semantic annotation is presented. A project Mem-ory concerns the representation and the identification of the experience acquired during projects realization. The main feature of this approach is that the semantic annotation is used to build a continuous semantic design rationale process. We propose in this paper, a semantic traceability in four stages (identifying, structuring, annotating and integrating). The identification and the structuring phases use a model called Extended Marguerite model which fully considers the objectives of the project memory. The annotation phase exploits the results of precedent phase to prepare the final phase. Examples are presented from a case study in an Algerian firm called ENMTP. The architecture supporting the modelling engine is presented. Finally, an evaluation of the degree of the semantic annotation brought by proposed process is given.展开更多
A main advantage of Architecture Description Languages (ADL) is their aptitude to facilitate formal analysis and verification of complex software architectures. Since some researchers try to extend them by new techniq...A main advantage of Architecture Description Languages (ADL) is their aptitude to facilitate formal analysis and verification of complex software architectures. Since some researchers try to extend them by new techniques, we show in this paper how the use of tile logic as extension of rewriting logic can enforce the ability of existing ADL formalisms to cope with hierarchy and composition features which are more and more present in such software architectures. In order to cover ADL key and generic concepts, our approach is explained through LfP (Language for rapid Prototyping) as ADL offering the possibility to specify the hierarchical behaviour of software components. Then, our contribution goal is to exploit a suitable logic that allows reasoning naturally about software system behaviour, possibly hierarchical and modular, in terms of its basic components and their interactions.展开更多
基金funded by the Research,Development,and Innovation Authority(RDIA)—Kingdom of Saudi Arabia—under supervision Energy,Industry,and Advanced Technologies Research Center,Taibah University,Madinah,Saudi Arabia with grant number(12979-iau-2023-TAU-R-3-1-EI-).
文摘The generation of high-quality 3D models from single 2D images remains challenging in terms of accuracy and completeness.Deep learning has emerged as a promising solution,offering new avenues for improvements.However,building models from scratch is computationally expensive and requires large datasets.This paper presents a transfer-learning-based approach for category-specific 3D reconstruction from a single 2D image.The core idea is to fine-tune a pre-trained model on specific object categories using new,unseen data,resulting in specialized versions of the model that are better adapted to reconstruct particular objects.The proposed approach utilizes a three-phase pipeline comprising image acquisition,3D reconstruction,and refinement.After ensuring the quality of the input image,a ResNet50 model is used for object recognition,directing the image to the corresponding category-specific model to generate a voxel-based representation.The voxel-based 3D model is then refined by transforming it into a detailed triangular mesh representation using the Marching Cubes algorithm and Laplacian smoothing.An experimental study,using the Pix2Vox model and the Pascal3D dataset,has been conducted to evaluate and validate the effectiveness of the proposed approach.Results demonstrate that category-specific fine-tuning of Pix2Vox significantly outperforms both the original model and the general model fine-tuned for all object categories,with substantial gains in Intersection over Union(IoU)scores.Visual assessments confirm improvements in geometric detail and surface realism.These findings indicate that combining transfer learning with category-specific fine tuning and refinement strategy of our approach leads to better-quality 3D model generation.
文摘UML 2.0 activity diagrams (ADs) are largely used as a modeling language for flow-oriented behaviors in software and business processes. Unfortunately, their place/transition operational semantics is unable to capture and preserve semantics of the newly defined high-level activities constructs such as Interruptible Activity Region. Particularly, basic Petri nets do not preserve the non-locality semantics and reactivity concept of ADs. This is mainly due to the absence of global synchronization mechanisms in basic Petri nets. Zero-safe nets are a high-level variant of Petri nets that ensure transitions global coordination thanks to a new kind of places, called zero places. Indeed, zero-safe nets naturally address Interruptible Activity Region that needs a special semantics, forcing the control flow by external events and defining a certain priority level of executions. Therefore, zero-safe nets are adopted in this work as semantic framework for UML 2.0 activity diagrams.
文摘In the proposal, a construction project memory process based on the semantic annotation is presented. A project Mem-ory concerns the representation and the identification of the experience acquired during projects realization. The main feature of this approach is that the semantic annotation is used to build a continuous semantic design rationale process. We propose in this paper, a semantic traceability in four stages (identifying, structuring, annotating and integrating). The identification and the structuring phases use a model called Extended Marguerite model which fully considers the objectives of the project memory. The annotation phase exploits the results of precedent phase to prepare the final phase. Examples are presented from a case study in an Algerian firm called ENMTP. The architecture supporting the modelling engine is presented. Finally, an evaluation of the degree of the semantic annotation brought by proposed process is given.
文摘A main advantage of Architecture Description Languages (ADL) is their aptitude to facilitate formal analysis and verification of complex software architectures. Since some researchers try to extend them by new techniques, we show in this paper how the use of tile logic as extension of rewriting logic can enforce the ability of existing ADL formalisms to cope with hierarchy and composition features which are more and more present in such software architectures. In order to cover ADL key and generic concepts, our approach is explained through LfP (Language for rapid Prototyping) as ADL offering the possibility to specify the hierarchical behaviour of software components. Then, our contribution goal is to exploit a suitable logic that allows reasoning naturally about software system behaviour, possibly hierarchical and modular, in terms of its basic components and their interactions.
