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

arXiv: https://arxiv.org/abs/1510.00477 · HTML: https://mlsanity.com/paper/1510.00477/

## Key facts

- Cited by 52 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 2 Oct 2015.

## Built on by (most cited first, 30 of 52)

- [Transparent Image Layer Diffusion using Latent Transparency](https://mlsanity.com/paper/2402.17113/) (2024)
- [Region-aware Adaptive Instance Normalization for Image Harmonization](https://mlsanity.com/paper/2106.02853/) (2021)
- [Making Images Real Again: A Comprehensive Survey on Deep Image Composition](https://mlsanity.com/paper/2106.14490/) (2021)
- [Harmonizer: Learning to Perform White-Box Image and Video Harmonization](https://mlsanity.com/paper/2207.01322/) (2022)
- [SSH: A Self-Supervised Framework for Image Harmonization](https://mlsanity.com/paper/2108.06805/) (2021)
- [Relightful Harmonization: Lighting-aware Portrait Background Replacement](https://mlsanity.com/paper/2312.06886/) (2023)
- [CAMPARI: Camera-Aware Decomposed Generative Neural Radiance Fields](https://mlsanity.com/paper/2103.17269/) (2021)
- [High-Resolution Image Harmonization via Collaborative Dual Transformations](https://mlsanity.com/paper/2109.06671/) (2021)
- [TransFill: Reference-guided Image Inpainting by Merging Multiple Color and Spatial Transformations](https://mlsanity.com/paper/2103.15982/) (2021)
- [Shadow Generation for Composite Image in Real-world Scenes](https://mlsanity.com/paper/2104.10338/) (2021)
- [Semi-supervised Parametric Real-world Image Harmonization](https://mlsanity.com/paper/2303.00157/) (2023)
- [Spatial-Separated Curve Rendering Network for Efficient and High-Resolution Image Harmonization](https://mlsanity.com/paper/2109.05750/) (2021)
- [SCS-Co: Self-Consistent Style Contrastive Learning for Image Harmonization](https://mlsanity.com/paper/2204.13962/) (2022)
- [Learning Object Placement via Dual-path Graph Completion](https://mlsanity.com/paper/2207.11464/) (2022)
- [Towards Enhanced Image Inpainting: Mitigating Unwanted Object Insertion and Preserving Color Consistency](https://mlsanity.com/paper/2312.04831/) (2023)
- [NCHO: Unsupervised Learning for Neural 3D Composition of Humans and Objects](https://mlsanity.com/paper/2305.14345/) (2023)
- [FreeCompose: Generic Zero-Shot Image Composition with Diffusion Prior](https://mlsanity.com/paper/2407.04947/) (2024)
- [Realistic Saliency Guided Image Enhancement](https://mlsanity.com/paper/2306.06092/) (2023)
- [3D-aware Blending with Generative NeRFs](https://mlsanity.com/paper/2302.06608/) (2023)
- [LEMaRT: Label-Efficient Masked Region Transform for Image Harmonization](https://mlsanity.com/paper/2304.13166/) (2023)
- [Painterly Image Harmonization using Diffusion Model](https://mlsanity.com/paper/2308.02228/) (2023)
- [Deep Image Harmonization in Dual Color Spaces](https://mlsanity.com/paper/2308.02813/) (2023)
- [Comprehensive Relighting: Generalizable and Consistent Monocular Human Relighting and Harmonization](https://mlsanity.com/paper/2504.03011/) (2025)
- [Painterly Image Harmonization in Dual Domains](https://mlsanity.com/paper/2212.08846/) (2022)
- [Memory-Driven Text-to-Image Generation](https://mlsanity.com/paper/2208.07022/) (2022)
- [Deep Video Harmonization with Color Mapping Consistency](https://mlsanity.com/paper/2205.00687/) (2022)
- [FRIH: Fine-grained Region-aware Image Harmonization](https://mlsanity.com/paper/2205.06448/) (2022)
- [Semantic-guided Multi-Mask Image Harmonization](https://mlsanity.com/paper/2207.11722/) (2022)
- [Foreground Object Search by Distilling Composite Image Feature](https://mlsanity.com/paper/2308.04990/) (2023)
- [Deep Image Harmonization with Learnable Augmentation](https://mlsanity.com/paper/2308.00376/) (2023)

## Abstract (arXiv)

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.