Photographic Image Synthesis with Cascaded Refinement Networks
arXiv:1707.09405
Abstract
We present an approach to synthesizing photographic images conditioned on semantic layouts. Given a semantic label map, our approach produces an image with photographic appearance that conforms to the input layout. The approach thus functions as a rendering engine that takes a two-dimensional semantic specification of the scene and produces a corresponding photographic image. Unlike recent and contemporaneous work, our approach does not rely on adversarial training. We show that photographic images can be synthesized from semantic layouts by a single feedforward network with appropriate structure, trained end-to-end with a direct regression objective. The presented approach scales seamlessly to high resolutions; we demonstrate this by synthesizing photographic images at 2-megapixel resolution, the full resolution of our training data. Extensive perceptual experiments on datasets of outdoor and indoor scenes demonstrate that images synthesized by the presented approach are considerably more realistic than alternative approaches. The results are shown in the supplementary video at https://youtu.be/0fhUJT21-bs
Published at the International Conference on Computer Vision (ICCV 2017)
References in corpus (7)
- Explaining and Harnessing Adversarial Examples
- Deep Generative Image Models using a Laplacian Pyramid of Adversarial Networks
- DRAW: A Recurrent Neural Network For Image Generation
- Generating Videos with Scene Dynamics
- Layer Normalization
- Visual Dynamics: Probabilistic Future Frame Synthesis via Cross Convolutional Networks
- DeepStereo: Learning to Predict New Views from the World's Imagery
Cited by in corpus (7)
- Unsupervised Portrait Shadow Removal via Generative Priors
- Personalized and Occupational-aware Age Progression by Generative Adversarial Networks
- PixelNN: Example-based Image Synthesis
- InverseNet: Solving Inverse Problems with Splitting Networks
- Pipeline Generative Adversarial Networks for Facial Images Generation with Multiple Attributes
- Instance Map based Image Synthesis with a Denoising Generative Adversarial Network
- Synthesizing Photorealistic Images with Deep Generative Learning