Graves, A., Schmidhuber, J.: Framewise phoneme classification with bidirectional LSTM and other neural network architectures. In: European Conference on Computer Vision (ECCV), pp. et al.: Microsoft coco: common objects in context. Journées Francaises d’Informatique Graphique et de Réalité virtuelle (2019) Bitmap or vector? A study on sketch representations for deep stroke segmentation. Hähnlein, F., Gryaditskaya, Y., Bousseau, A. Yang, L., et al.: Sketchgnn: semantic sketch segmentation with graph neural networks. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. et al.: Universal sketch perceptual grouping. Kaiyrbekov, K., Sezgin, M.: Deep stroke-based sketched symbol reconstruction and segmentation. Li, K., et al.: Toward deep universal sketch perceptual grouper. Qi, Y., Tan, Z.-H.: Sketchsegnet+: an end-to-end learning of RNN for multi-class sketch semantic segmentation.
In: 2018 IEEE 28th International Workshop on Machine Learning for Signal Processing (MLSP), pp. Wu, X., Qi, Y., Liu, J., Yang, J.: Sketchsegnet: a RNN model for labeling sketch strokes.
In: Proceedings of the 25th ACM International Conference on Multimedia, pp. Sarvadevabhatla, R.K., Dwivedi, I., Biswas, A., Manocha, S.: Sketchparse: towards rich descriptions for poorly drawn sketches using multi-task hierarchical deep networks. Zhu, X., Xiao, Y., Zheng, Y.: 2d freehand sketch labeling using CNN and CRF. Wang, F., et al.: Multi-column point-CNN for sketch segmentation. Li, L., Fu, H., Tai, C.-L.: Fast sketch segmentation and labeling with deep learning. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. Qi, Y., et al.: Making better use of edges via perceptual grouping. Huang, Z., Fu, H., Lau, R.W.: Data-driven segmentation and labeling of freehand sketches. Schneider, R.G., Tuytelaars, T.: Example-based sketch segmentation and labeling using CRFS.
#HUMAN SKETCH FREE#
Sun, Z., Wang, C., Zhang, L., Zhang, L.: Free hand-drawn sketch segmentation. Gennari, L., Kara, L.B., Stahovich, T.F., Shimada, K.: Combining geometry and domain knowledge to interpret hand-drawn diagrams. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp 799–807 (2016)ĭelaye, A., Lee, K.: A flexible framework for online document segmentation by pairwise stroke distance learning. Sangkloy, P., Burnell, N., Ham, C., Hays, J.: The sketchy database: learning to retrieve badly drawn bunnies. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. Gao, C., et al.: Sketchycoco: image generation from freehand scene sketches. In: International Conference on Learning Representations (ICLR) (2018) Ha, D., Eck, D.A.: Neural representation of sketch drawings. 421–436 (2018)Įitz, M., Hays, J., Alexa, M.: How do humans sketch objects? ACM Trans. et al.: Sketchyscene: Richly-annotated scene sketches.
The code, models, and dataset will be made public after acceptance. The experimental results demonstrate that our method outperforms state-of-the-art methods. We conduct comparative and ablative experiments on SFSD to evaluate the effectiveness of our method. SFSD is composed of 12K sketch-photo pairs over 40 object categories, where the sketches were completely hand-drawn and each contains 7 objects on average. In order to address the data lacking issue, we propose the first scene-level free-hand sketch dataset (SFSD). In this paper, we present a new stroke-based sequential-spatial neural network (S \(^3\)NN) for scene-level free-hand sketch semantic segmentation, which leverages a bidirectional LSTM and graph convolutional network to capture the sequential and spatial features of sketches. The existing sketch semantic segmentation methods are mainly designed for single-instance sketches. Due to modality difference between images and sketches, existing image segmentation methods may not perform best, which overlook the sparse nature and stroke-based representation in sketches. Sketch semantic segmentation plays a key role in sketch understanding and is widely used in sketch recognition, sketch-based image retrieval, or editing. Sketching is a simple and efficient way for humans to express their perceptions of the world.
0 kommentar(er)
