Learning a Discriminative Model for the Perception of Realism in Composite Images

Abstract

What makes an image appear realistic? In this work, we are answering this question from a data-driven perspective by learning the perception of visual realism directly from large amounts of data. In particular, we train a Convolutional Neural Network (CNN) model that distinguishes natural photographs from automatically generated composite images. The model learns to predict visual realism of a scene in terms of color, lighting and texture compatibility, without any human annotations pertaining to it. Our model outperforms previous works that rely on hand-crafted heuristics, for the task of classifying realistic vs. unrealistic photos. Furthermore, we apply our learned model to compute optimal parameters of a compositing method, to maximize the visual realism score predicted by our CNN model. We demonstrate its advantage against existing methods via a human perception study.

International Conference on Computer Vision (ICCV) 2015

References in corpus (2)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• Caffe: Convolutional Architecture for Fast Feature Embedding

Cited by in corpus (10)

• Improving the Harmony of the Composite Image by Spatial-Separated Attention Module
• GP-GAN: Towards Realistic High-Resolution Image Blending
• Data Augmentation for Object Detection via Progressive and Selective Instance-Switching
• ST-GAN: Spatial Transformer Generative Adversarial Networks for Image Compositing
• Real-Time User-Guided Image Colorization with Learned Deep Priors
• Deep Image Harmonization
• Semi-parametric Image Synthesis
• Deep Matching and Validation Network -- An End-to-End Solution to Constrained Image Splicing Localization and Detection
• Where and Who? Automatic Semantic-Aware Person Composition
• Temporally Coherent Video Harmonization Using Adversarial Networks