We propose a robust and highly realistic clothing modeling method to generate a 3D clothing model with visually consistent clothing style and wrinkles distribution from a single RGB image. Notably, this entire process only takes a few seconds. Our high-quality clothing results benefit from the idea of combining learning and optimization, making it highly robust. First, we use the neural networks to predict the normal map, a clothing mask, and a learning-based clothing model from input images. The predicted normal map can effectively capture high-frequency clothing deformation from image observations. Then, by introducing a normal-guided clothing fitting optimization, the normal maps are used to guide the clothing model to generate realistic wrinkles details. Finally, we utilize a clothing collar adjustment strategy to stylize clothing results using predicted clothing masks. An extended multi-view version of the clothing fitting is naturally developed, which can further improve the realism of the clothing without tedious effort. Extensive experiments have proven that our method achieves state-of-the-art clothing geometric accuracy and visual realism. More importantly, it is highly adaptable and robust to in-the-wild images. Further, our method can be easily extended to multi-view inputs to improve realism. In summary, our method can provide a low-cost and user-friendly solution to achieve realistic clothing modeling.

Garment customization means that clients can provide their individual information for creating garments that fit them well. It has become a trend in garment industry. Three-dimensional (3D) methods have been emerging and have proved to be intuitive and effective ways for garment customization. In this paper, we propose a novel 3D garment customization approach based on a feature curve-net. A feature curve-net is weaved by feature curves that are initially extracted from 3D human models and then fitted onto 3D garment models. Three-dimensional garment models are locally parameterized on the feature curve-nets by applying bicubic Coons surface technology. Feature curve-nets created from different human models have the same topology connectivity. Thus, garment models on a reference human model can be transferred onto a target human model by reconstructing the garment models from the feature curve-net on the target human model. The shapes of the customized garment models can be further conveniently altered by interactively editing the feature curve-net. Our method supports both the 3D garment resizing and 3D garment editing, while most existing 3D garment customization methods can only support 3D garment resizing. Our method is flexible and can be useful in garment customization.

Sketch-based modeling studies reconstructing models from sketches automatically, allowing users visualize design concepts rapidly. Generating CAD models based on user sketches helps reduce the learning curve for novice users, which promotes the everyday use of CAD software, and expands its reach to non-professional groups. While various algorithms study automatically generating models from single sketch or line drawing, they often produce non-editable models or editable models limited to simple extrusion operations. To improve this issue, we propose a novel sketch-based modeling system, Sketch2Seq, which generates complex, semantic, and editable CAD models. Our system eliminates the need for additional annotations from users and produces models that support subsequent application in commercial software. The core of our method lies in understanding users' design intent from CAD sketches. We design a novel sketch segmentation network for identifying diverse operation features in CAD sketches, which utilizes geometric features of strokes and different levels of topological connections. Additionally, to tackle the segmentation task, a dataset for CAD sketch segmentation is introduced. Comparative experiments and ablation evaluations prove the effectiveness of the proposed method. Based on segmentation result, coarse CAD sequences are generated and progressively executed. Meanwhile, the orders and parameters of the CAD sequences are optimized with context models and input sketches. All algorithms are integrated into a user interface. Experiments and evaluations validate the feasibility and superiority of our entire system which is able to reconstruct more complex features and achieve better results for longer sequence.