# Deep Image Harmonization in Dual Color Spaces

arXiv: https://arxiv.org/abs/2308.02813 · HTML: https://mlsanity.com/paper/2308.02813/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- Builds on 32 of its 50 references that are in the map.
- First posted on arXiv 5 Aug 2023.

## Builds on (most cited first, 30 of 32)

- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [Analyzing and Improving the Image Quality of StyleGAN](https://mlsanity.com/paper/1912.04958/) (2019)
- [Adaptive Computation Time for Recurrent Neural Networks](https://mlsanity.com/paper/1603.08983/) (2016)
- [Dynamic Convolution: Attention over Convolution Kernels](https://mlsanity.com/paper/1912.03458/) (2019)
- [CondConv: Conditionally Parameterized Convolutions for Efficient Inference](https://mlsanity.com/paper/1904.04971/) (2019)
- [DoveNet: Deep Image Harmonization via Domain Verification](https://mlsanity.com/paper/1911.13239/) (2019)
- [Underwater Image Enhancement via Medium Transmission-Guided Multi-Color Space Embedding](https://mlsanity.com/paper/2104.13015/) (2021)
- [Pixel-Adaptive Convolutional Neural Networks](https://mlsanity.com/paper/1904.05373/) (2019)
- [Deep Image Harmonization](https://mlsanity.com/paper/1703.00069/) (2017)
- [U-shape Transformer for Underwater Image Enhancement](https://mlsanity.com/paper/2111.11843/) (2021)
- [MAST: A Memory-Augmented Self-supervised Tracker](https://mlsanity.com/paper/2002.07793/) (2020)
- [Improving the Harmony of the Composite Image by Spatial-Separated Attention Module](https://mlsanity.com/paper/1907.06406/) (2019)
- [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)
- [High-Resolution Image Harmonization via Collaborative Dual Transformations](https://mlsanity.com/paper/2109.06671/) (2021)
- [Foreground-aware Semantic Representations for Image Harmonization](https://mlsanity.com/paper/2006.00809/) (2020)
- [Learning a Discriminative Model for the Perception of Realism in Composite Images](https://mlsanity.com/paper/1510.00477/) (2015)
- [BargainNet: Background-Guided Domain Translation for Image Harmonization](https://mlsanity.com/paper/2009.09169/) (2020)
- [DCCF: Deep Comprehensible Color Filter Learning Framework for High-Resolution Image Harmonization](https://mlsanity.com/paper/2207.04788/) (2022)
- [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)
- [A Wavelet-based Dual-stream Network for Underwater Image Enhancement](https://mlsanity.com/paper/2202.08758/) (2022)
- [Deep Image Harmonization by Bridging the Reality Gap](https://mlsanity.com/paper/2103.17104/) (2021)
- [Deep Image-based Illumination Harmonization](https://mlsanity.com/paper/2108.00150/) (2021)
- [Painterly Image Harmonization in Dual Domains](https://mlsanity.com/paper/2212.08846/) (2022)
- [FRIH: Fine-grained Region-aware Image Harmonization](https://mlsanity.com/paper/2205.06448/) (2022)
- [Image Harmonization by Matching Regional References](https://mlsanity.com/paper/2204.04715/) (2022)
- [Semantic-guided Multi-Mask Image Harmonization](https://mlsanity.com/paper/2207.11722/) (2022)

## Built on by (most cited first, 12 of 12)

- [Transparent Image Layer Diffusion using Latent Transparency](https://mlsanity.com/paper/2402.17113/) (2024)
- [Relightful Harmonization: Lighting-aware Portrait Background Replacement](https://mlsanity.com/paper/2312.06886/) (2023)
- [FreeCompose: Generic Zero-Shot Image Composition with Diffusion Prior](https://mlsanity.com/paper/2407.04947/) (2024)
- [DeCo: Decoupled Human-Centered Diffusion Video Editing with Motion Consistency](https://mlsanity.com/paper/2408.07481/) (2024)
- [DreamLight: Towards Harmonious and Consistent Image Relighting](https://mlsanity.com/paper/2506.14549/) (2025)
- [HarmonyIQA: Pioneering Benchmark and Model for Image Harmonization Quality Assessment](https://mlsanity.com/paper/2501.01116/) (2025)
- [DiffHarmony: Latent Diffusion Model Meets Image Harmonization](https://mlsanity.com/paper/2404.06139/) (2024)
- [VIBE: Visual Instruction Based Editor](https://mlsanity.com/paper/2601.02242/) (2026)
- [Painterly Image Harmonization via Adversarial Residual Learning](https://mlsanity.com/paper/2311.08646/) (2023)
- [PHNet: Patch-based Normalization for Portrait Harmonization](https://mlsanity.com/paper/2402.17561/) (2024)
- [Harmonizing Attention: Training-free Texture-aware Geometry Transfer](https://mlsanity.com/paper/2408.10846/) (2024)
- [HarmoniDiff-RS: Training-Free Diffusion Harmonization for Satellite Image Composition](https://mlsanity.com/paper/2604.19392/) (2026)

## Abstract (arXiv)

Image harmonization is an essential step in image composition that adjusts the appearance of composite foreground to address the inconsistency between foreground and background. Existing methods primarily operate in correlated RGB color space, leading to entangled features and limited representation ability. In contrast, decorrelated color space (e.g., Lab) has decorrelated channels that provide disentangled color and illumination statistics. In this paper, we explore image harmonization in dual color spaces, which supplements entangled RGB features with disentangled L, a, b features to alleviate the workload in harmonization process. The network comprises a RGB harmonization backbone, an Lab encoding module, and an Lab control module. The backbone is a U-Net network translating composite image to harmonized image. Three encoders in Lab encoding module extract three control codes independently from L, a, b channels, which are used to manipulate the decoder features in harmonization backbone via Lab control module. Our code and model are available at hrefhttps://github.com/bcmi/DucoNet-Image-Harmonizationhttps://github.com/bcmi/DucoNet-Image-Harmonization.