Automatic floor plan generation is a long-standing goal in the field of engineering and architectural design. It has significant value in practical applications. Although extensive research over several decades has introduced numerous innovative methods, the issue remains a significant challenge. In this study, we introduce a novel approach to floor plan image generation, leveraging the capabilities of the large pre-trained Latent Diffusion Model (LDM). Through improvements in the architecture of the pre-trained Latent Diffusion Model (LDM) and subsequent fine-tuning, we achieve an effective multimodal conditional floor plan image generation with a reduced amount of training data. Specifically, we propose a multi-head self-attention graph convolution-based layout embedding and a novel layout fusion contrast learning module integrating to the pre-trained LDM, which not only enhances the constraint generation under layout instructions, but also preserves the balance and consistency of the floor plan elements, such as different kinds of rooms and walls, as specified in the textual instructions. The experiments were conducted on two commonly used data sets, RPLAN and LIFULL. The experimental results show that our method outperforms the traditional methods and SOTA work and achieves the best generation results.

In the rapidly evolving field of manufacturing industry, product designers need to be able to quickly and accurately retrieve and reference existing Computer-Aided Design (CAD) primitives to increase efficiency and foster innovation. This paper introduces an innovative deep hashing-based parametric CAD primitive retrieval model DH-CAD, which employs a deep learning framework to capture the profound multi-modal features of parametric CAD primitive (command sequences and point clouds), and utilizes hashing to effectively encode these features into compact binary hash codes, significantly improving retrieval efficiency and accuracy. DH-CAD optimizes the original sequence encodings of Transformer to effectively learn the intricate relationships between CAD tool's command sequences and the corresponding point clouds of CAD primitive. Furthermore, it considers the dependencies between command types and parameter values, combines the output of the command type decoder with the prediction of parameter values to further refine the generated parameters, and employs a binarization network to generate hash codes in an end-to-end manner. Experimental results clearly demonstrate that, compared to traditional feature-matching methods, DH-CAD achieves the state-of-the-art performance on multiple evaluation metrics. Particularly in terms of retrieval speed and accuracy, our proposed model not only retrieves sequences that are most relevant to the query rapidly, but also ensures the high precision of the results, showcasing its efficiency and practicality in supporting CAD design processes.

CAD models are multimodal data where information and knowledge contained in construction sequences and shapes are complementary to each other and representation learning methods should consider both of them. Such traits have been neglected in previous methods learning unimodal representations. To leverage the information from both modalities, we develop a multimodal contrastive learning strategy where features from different modalities interact via contrastive learning paradigm, driven by a novel multimodal contrastive loss. Two pretext tasks on both geometry and sequence domains are designed along with a two-stage training strategy to make the representation focus on encoding geometric details and decoding representations into construction sequences, thus being more applicable to downstream tasks such as multimodal retrieval and CAD sequence reconstruction. Experimental results show that the performance of our multimodal representation learning scheme has surpassed the baselines and unimodal methods significantly.

Deep generative modeling on parametric Computer-Aided Design (CAD) data has great potentials in various industrial scenarios. However, the reasonable data augmentation for parametric CAD has not been solved yet, which limits the performance of the deep learning on parametric CAD data. Unlike images or language, parametric CAD data involves dual-aspects: command sequence and geometric shape. Hence, most previous data augmentation methods are unsuitable for this problem. To address this issue, we propose a novel mix-based augmentation method, namely Twins-Mix, keeping a well balance between the diversity and the validity of parametric CAD sequences, which significantly boost the performance of CAD generative modeling. Comprehensive experiments are conducted on the commonly used benchmark datasets, i.e., Fusion 360 and DeepCAD. The experimental results demonstrate that our model exceeds other comparable augmentations on CAD generative modeling significantly, especially in increasing the valid 3D shape construction ratio by at least more than 4%.

Abstract Artificial bee colony (ABC) performs excellently over many problems, but it has some shortcomings, such as weak exploitation as well as slow convergence. For the sake of dealing with these issues, a modified ABC known as MPABC is presented. Firstly, the entire population is partitioned into two different subpopulations at the stage of employed bees, and they use different search strategies. Then, a new probability selection strategy is designed on the basis of the principle of Soft Maximum function. Finally, a novel search method is constructed for improving the intensity of exploitation by gradually increasing the ratio of the current optimal solutions. In order to comprehensively validate the capability of MPABC, 12 benchmark problems are employed. Computational results clearly demonstrate MPABC surpasses the basic ABC and some other famous ABCs.