Depth Structure Preserving Scene Image Generation
arXiv:1706.00212
Abstract
Key to automatically generate natural scene images is to properly arrange among various spatial elements, especially in the depth direction. To this end, we introduce a novel depth structure preserving scene image generation network (DSP-GAN), which favors a hierarchical and heterogeneous architecture, for the purpose of depth structure preserving scene generation. The main trunk of the proposed infrastructure is built on a Hawkes point process that models the spatial dependency between different depth layers. Within each layer generative adversarial sub-networks are trained collaboratively to generate realistic scene components, conditioned on the layer information produced by the point process. We experiment our model on a sub-set of SUNdataset with annotated scene images and demonstrate that our models are capable of generating depth-realistic natural scene image.
There is an error in the first paragraph in Section 4.4. Actually, we train and test another new CGAN model with the input in our model to evaluate the improvements. This error can lead readers misunderstand the improvements of our model and make the comparison unfair. Therefore, we request to withdraw the current submission and will submit a final version later
References in corpus (11)
- Conditional Generative Adversarial Nets
- Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks
- Tutorial on Variational Autoencoders
- InfoGAN: Interpretable Representation Learning by Information Maximizing Generative Adversarial Nets
- DRAW: A Recurrent Neural Network For Image Generation
- Energy-based Generative Adversarial Network
- Synthesizing the preferred inputs for neurons in neural networks via deep generator networks
- Neural Photo Editing with Introspective Adversarial Networks
- Loss-Sensitive Generative Adversarial Networks on Lipschitz Densities
- Attribute2Image: Conditional Image Generation from Visual Attributes
- Generating Images Part by Part with Composite Generative Adversarial Networks