# Deep Image Harmonization by Bridging the Reality Gap arXiv: https://arxiv.org/abs/2103.17104 ยท HTML: https://mlsanity.com/paper/2103.17104/ ## Key facts - Cited by 11 papers in the map (data through 14 Oct 2026). - Builds on 31 of its 62 references that are in the map. - First posted on arXiv 31 Mar 2021. ## Builds on (most cited first, 30 of 31) - [Image-to-Image Translation with Conditional Adversarial Networks](https://mlsanity.com/paper/1611.07004/) (2016) - [Domain-Adversarial Training of Neural Networks](https://mlsanity.com/paper/1505.07818/) (2015) - [CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Features](https://mlsanity.com/paper/1905.04899/) (2019) - [Unsupervised Domain Adaptation by Backpropagation](https://mlsanity.com/paper/1409.7495/) (2014) - [Adversarial Discriminative Domain Adaptation](https://mlsanity.com/paper/1702.05464/) (2017) - [StarGAN: Unified Generative Adversarial Networks for Multi-Domain Image-to-Image Translation](https://mlsanity.com/paper/1711.09020/) (2017) - [Multimodal Unsupervised Image-to-Image Translation](https://mlsanity.com/paper/1804.04732/) (2018) - [Contrastive Learning for Unpaired Image-to-Image Translation](https://mlsanity.com/paper/2007.15651/) (2020) - [ADVENT: Adversarial Entropy Minimization for Domain Adaptation in Semantic Segmentation](https://mlsanity.com/paper/1811.12833/) (2018) - [Unsupervised Image-to-Image Translation Networks](https://mlsanity.com/paper/1703.00848/) (2017) - [Person Transfer GAN to Bridge Domain Gap for Person Re-Identification](https://mlsanity.com/paper/1711.08565/) (2017) - [Domain Adaptive Faster R-CNN for Object Detection in the Wild](https://mlsanity.com/paper/1803.03243/) (2018) - [Diverse Image-to-Image Translation via Disentangled Representations](https://mlsanity.com/paper/1808.00948/) (2018) - [DRIT++: Diverse Image-to-Image Translation via Disentangled Representations](https://mlsanity.com/paper/1905.01270/) (2019) - [Few-Shot Unsupervised Image-to-Image Translation](https://mlsanity.com/paper/1905.01723/) (2019) - [Cross-Domain Weakly-Supervised Object Detection through Progressive Domain Adaptation](https://mlsanity.com/paper/1803.11365/) (2018) - [Image-Image Domain Adaptation with Preserved Self-Similarity and Domain-Dissimilarity for Person Re-identification](https://mlsanity.com/paper/1711.07027/) (2017) - [DoveNet: Deep Image Harmonization via Domain Verification](https://mlsanity.com/paper/1911.13239/) (2019) - [Deep Image Harmonization](https://mlsanity.com/paper/1703.00069/) (2017) - [Curriculum Domain Adaptation for Semantic Segmentation of Urban Scenes](https://mlsanity.com/paper/1707.09465/) (2017) - [Cross-modal Deep Variational Hand Pose Estimation](https://mlsanity.com/paper/1803.11404/) (2018) - [Self-Training and Adversarial Background Regularization for Unsupervised Domain Adaptive One-Stage Object Detection](https://mlsanity.com/paper/1909.00597/) (2019) - [Improving the Harmony of the Composite Image by Spatial-Separated Attention Module](https://mlsanity.com/paper/1907.06406/) (2019) - [Adversarial-Learned Loss for Domain Adaptation](https://mlsanity.com/paper/2001.01046/) (2020) - [Foreground-aware Semantic Representations for Image Harmonization](https://mlsanity.com/paper/2006.00809/) (2020) - [BargainNet: Background-Guided Domain Translation for Image Harmonization](https://mlsanity.com/paper/2009.09169/) (2020) - [Multi-Evidence Filtering and Fusion for Multi-Label Classification, Object Detection and Semantic Segmentation Based on Weakly Supervised Learning](https://mlsanity.com/paper/1802.09129/) (2018) - [Fine-grained Recognition in the Wild: A Multi-Task Domain Adaptation Approach](https://mlsanity.com/paper/1709.02476/) (2017) - [Where and Who? Automatic Semantic-Aware Person Composition](https://mlsanity.com/paper/1706.01021/) (2017) - [Unsupervised Domain Adaptation for 3D Keypoint Estimation via View Consistency](https://mlsanity.com/paper/1712.05765/) (2017) ## Built on by (most cited first, 11 of 11) - [Making Images Real Again: A Comprehensive Survey on Deep Image Composition](https://mlsanity.com/paper/2106.14490/) (2021) - [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) - [Deep Image Harmonization with Globally Guided Feature Transformation and Relation Distillation](https://mlsanity.com/paper/2308.00356/) (2023) - [SIDNet: Learning Shading-aware Illumination Descriptor for Image Harmonization](https://mlsanity.com/paper/2112.01314/) (2021) - [Inharmonious Region Localization with Auxiliary Style Feature](https://mlsanity.com/paper/2210.02029/) (2022) - [ConsiStyle: Style Diversity in Training-Free Consistent T2I Generation](https://mlsanity.com/paper/2505.20626/) (2025) - [Inharmonious Region Localization via Recurrent Self-Reasoning](https://mlsanity.com/paper/2210.02036/) (2022) - [PHNet: Patch-based Normalization for Portrait Harmonization](https://mlsanity.com/paper/2402.17561/) (2024) - [Region-to-Region: Enhancing Generative Image Harmonization with Adaptive Regional Injection](https://mlsanity.com/paper/2508.09746/) (2025) ## Abstract (arXiv) Image harmonization has been significantly advanced with large-scale harmonization dataset. However, the current way to build dataset is still labor-intensive, which adversely affects the extendability of dataset. To address this problem, we propose to construct rendered harmonization dataset with fewer human efforts to augment the existing real-world dataset. To leverage both real-world images and rendered images, we propose a cross-domain harmonization network to bridge the domain gap between two domains. Moreover, we also employ well-designed style classifiers and losses to facilitate cross-domain knowledge transfer. Extensive experiments demonstrate the potential of using rendered images for image harmonization and the effectiveness of our proposed network.