Diverse Image Harmonization
Not on the map. Why?
Abstract (arXiv)
Image harmonization aims to adjust the foreground illumination in a composite image to make it harmonious. The existing harmonization methods can only produce one deterministic result for a composite image, ignoring that a composite image could have multiple plausible harmonization results due to multiple plausible reflectances. In this work, we first propose a reflectance-guided harmonization network, which can achieve better performance with the guidance of ground-truth foreground reflectance. Then, we also design a diverse reflectance generation network to predict multiple plausible foreground reflectances, leading to multiple plausible harmonization results. The extensive experiments on the benchmark datasets demonstrate the effectiveness of our method.
Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 34 of its 49 references that are in the map. First posted on arXiv 22 Jul 2024.
Builds on
34 of 49 references.
References · 34
- 2017Neural Discrete Representation Learningcited by 4,650
- 2013Auto-Encoding Variational Bayescited by 3,980
- 2019Analyzing and Improving the Image Quality of StyleGANcited by 3,580
- 2014Conditional Generative Adversarial Netscited by 2,152
- 2016Least Squares Generative Adversarial Networkscited by 1,000
- 2016InfoGAN: Interpretable Representation Learning by Information Maximizing Generative Adversarial Netscited by 858
- 2018Image Inpainting for Irregular Holes Using Partial Convolutionscited by 505
- 2015Autoencoding beyond pixels using a learned similarity metriccited by 407
- 2016Adversarially Learned Inferencecited by 216
- 2019Pluralistic Image Completioncited by 162
- 2019DoveNet: Deep Image Harmonization via Domain Verificationcited by 134
- 2021High-Fidelity Pluralistic Image Completion with Transformerscited by 134
22 more
- 2017Deep Image Harmonizationcited by 120
- 2019Improving the Harmony of the Composite Image by Spatial-Separated Attention Modulecited by 73
- 2021Region-aware Adaptive Instance Normalization for Image Harmonizationcited by 71
- 2021Making Images Real Again: A Comprehensive Survey on Deep Image Compositioncited by 63
- 2022Harmonizer: Learning to Perform White-Box Image and Video Harmonizationcited by 61
- 2021SSH: A Self-Supervised Framework for Image Harmonizationcited by 60
- 2021High-Resolution Image Harmonization via Collaborative Dual Transformationscited by 55
- 2020Foreground-aware Semantic Representations for Image Harmonizationcited by 53
- 2015Learning a Discriminative Model for the Perception of Realism in Composite Imagescited by 52
- 2021Self-supervised Outdoor Scene Relightingcited by 48
- 2022DCCF: Deep Comprehensible Color Filter Learning Framework for High-Resolution Image Harmonizationcited by 46
- 2022Reduce Information Loss in Transformers for Pluralistic Image Inpaintingcited by 36
- 2023Semi-supervised Parametric Real-world Image Harmonizationcited by 26
- 2021Spatial-Separated Curve Rendering Network for Efficient and High-Resolution Image Harmonizationcited by 25
- 2022SCS-Co: Self-Consistent Style Contrastive Learning for Image Harmonizationcited by 24
- 2023Dense Pixel-to-Pixel Harmonization via Continuous Image Representationcited by 19
- 2019PiiGAN: Generative Adversarial Networks for Pluralistic Image Inpaintingcited by 17
- 2023LEMaRT: Label-Efficient Masked Region Transform for Image Harmonizationcited by 12
- 2021Deep Image-based Illumination Harmonizationcited by 11
- 2017PixelNN: Example-based Image Synthesiscited by 7
- 2022Semantic-guided Multi-Mask Image Harmonizationcited by 6
- 2023Learning Global-aware Kernel for Image Harmonizationcited by 4
Built on by
Citing papers per year: 2026: 1.
1 paper.