![]() Yu, Q., Yang, Y., Song, Y.Z., Xiang, T., Hospedales, T.: Sketch-a-net that beats humans. Yu, Q., Yang, Y., Liu, F., Song, Y.Z., Xiang, T., Hospedales, T.: Sketch-a-net: a deep neural network that beats humans. Sutton, R.S., McAllester, D.A., Singh, S.P., Mansour, Y.: Policy gradient methods for reinforcement learning with function approximation. ![]() Srivastava, N., Mansimov, E., Salakhudinov, R.: Unsupervised learning of video representations using LSTMs. Song, J., Pang, K., Song, Y., Xiang, T., Hospedales, T.M.: Learning to sketch with shortcut cycle consistency. ![]() Shao, L., Zhou, H.: Curve fitting with Bezier cubics. Sangkloy, P., Burnell, N., Ham, C., Hays, J.: The sketchy database: learning to retrieve badly drawn bunnies. Salomon, D.: Curves and Surfaces for Computer Graphics. Romaszko, L., Williams, C.K.I., Moreno, P., Kohli, P.: Vision-as-inverse-graphics: obtaining a rich 3D explanation of a scene from a single image. Revow, M., Williams, C.K.I., Hinton, G.E.: Using generative models for handwritten digit recognition. Radford, A., Metz, L., Chintala, S.: Unsupervised representation learning with deep convolutional generative adversarial networks. Rabiner, L., Juang, B.: An introduction to hidden Markov models. Plass, M., Stone, M.: Curve-fitting with piecewise parametric cubics. Pang, K., et al.: Generalising fine-grained sketch-based image retrieval. In: Huang, D.-S., Zhang, X., Reyes García, C.A., Zhang, L. Masood, A., Ejaz, S.: An efficient algorithm for robust curve fitting using cubic Bezier curves. Marti, U.V., Bunke, H.: A full English sentence database for off-line handwriting recognition. Lopes, R.G., Ha, D., Eck, D., Shlens, J.: A learned representation for scalable vector graphics. Liu, Y., Wang, W.: A revisit to least squares orthogonal distance fitting of parametric curves and surfaces. In: 2018 International Conference on 3D Vision (3DV) (2018) Laube, P., Franz, M.O., Umlauf, G.: Deep learning parametrization for B-spline curve approximation. Lake, B.M., Salakhutdinov, R., Tenenbaum, J.B.: Human-level concept learning through probabilistic program induction. Kulkarni, T.D., Whitney, W., Kohli, P., Tenenbaum, J.B.: Deep convolutional inverse graphics network. Klare, B., Li, Z., Jain, A.: Matching forensic sketches to mug shot photos. Kingma, D.P., Welling, M.: Auto-encoding variational bayes. Isola, P., Zhu, J.Y., Zhou, T., Efros, A.A.: Image-to-image translation with conditional adversarial networks. Hinton, G.E., Salakhutdinov, R.R.: Reducing the dimensionality of data with neural networks. Heusel, M., Ramsauer, H., Unterthiner, T., Nessler, B., Hochreiter, S.: GANs trained by a two time-scale update rule converge to a local nash equilibrium. Ha, D., Eck, D.: A neural representation of sketch drawings. Graves, A.: Generating sequences with recurrent neural networks. Goodfellow, I., et al.: Generative adversarial nets. Ganin, Y., Kulkarni, T., Babuschkin, I., Eslami, S.M.A., Vinyals, O.: Synthesizing programs for images using reinforced adversarial learning. Springer, New York (1978)ĭey, S., Riba, P., Dutta, A., Llados, J., Song, Y.Z.: Doodle to search: practical zero-shot sketch-based image retrieval. In: CoNLL (2016)ĭe Boor, C., De Boor, C., Mathématicien, E.U., De Boor, C., De Boor, C.: A Practical Guide to Splines, vol. ![]() Technical report, Aston University (1994)īowman, S.R., Vilnis, L., Vinyals, O., Dai, A., Jozefowicz, R., Bengio, S.: Generating sentences from a continuous space. Keywordsīishop, C.M.: Mixture density networks. We report qualitative and quantitative results on the Quick, Draw! benchmark. This enables us to treat sketches as short sequences of paramaterized strokes and thus train a recurrent sketch generator with greater capacity for longer sketches, while producing scalable high-resolution results. To this end, we first introduce a novel inverse graphics approach to stroke embedding that trains an encoder to embed each stroke to its best fit Bézier curve. In this paper we present BézierSketch, a novel generative model for fully vector sketches that are automatically scalable and high-resolution. However this leads to low-resolution image generation, and failure to model long sketches. The landmark SketchRNN provided breakthrough by sequentially generating sketches as a sequence of waypoints. The study of neural generative models of human sketches is a fascinating contemporary modeling problem due to the links between sketch image generation and the human drawing process.
0 Comments
Leave a Reply. |