Guiding Users to Where to Give Color Hints for Efficient Interactive Sketch Colorization via Unsupervised Region Prioritization
Not on the map. Why?
Abstract (arXiv)
Existing deep interactive colorization models have focused on ways to utilize various types of interactions, such as point-wise color hints, scribbles, or natural-language texts, as methods to reflect a user's intent at runtime. However, another approach, which actively informs the user of the most effective regions to give hints for sketch image colorization, has been under-explored. This paper proposes a novel model-guided deep interactive colorization framework that reduces the required amount of user interactions, by prioritizing the regions in a colorization model. Our method, called GuidingPainter, prioritizes these regions where the model most needs a color hint, rather than just relying on the user's manual decision on where to give a color hint. In our extensive experiments, we show that our approach outperforms existing interactive colorization methods in terms of the conventional metrics, such as PSNR and FID, and reduces required amount of interactions.
Key facts. Cited by 3 papers in the map (data through 7 Oct 2026). Builds on 32 of its 44 references that are in the map. First posted on arXiv 25 Oct 2022.
Builds on
32 of 44 references.
References · 32
- 2014Adam: A Method for Stochastic Optimizationcited by 36,960
- 2016Image-to-Image Translation with Conditional Adversarial Networkscited by 4,510
- 2014Deep Learning Face Attributes in the Wildcited by 3,679
- 2016Categorical Reparameterization with Gumbel-Softmaxcited by 2,708
- 2014Conditional Generative Adversarial Netscited by 2,152
- 2016The Concrete Distribution: A Continuous Relaxation of Discrete Random Variablescited by 1,135
- 2016Colorful Image Colorizationcited by 1,113
- 2016Least Squares Generative Adversarial Networkscited by 1,000
- 2017Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networkscited by 707
- 2017AttnGAN: Fine-Grained Text to Image Generation with Attentional Generative Adversarial Networkscited by 664
- 2019MaskGAN: Towards Diverse and Interactive Facial Image Manipulationcited by 624
- 2016Generative Visual Manipulation on the Natural Image Manifoldcited by 348
20 more
- 2016Segmentation from Natural Language Expressionscited by 257
- 2017Real-Time User-Guided Image Colorization with Learned Deep Priorscited by 123
- 2019SC-FEGAN: Face Editing Generative Adversarial Network with User's Sketch and Colorcited by 105
- 2018Text-Adaptive Generative Adversarial Networks: Manipulating Images with Natural Languagecited by 90
- 2016Scribbler: Controlling Deep Image Synthesis with Sketch and Colorcited by 77
- 2020Instance-aware Image Colorizationcited by 76
- 2020Reference-Based Sketch Image Colorization using Augmented-Self Reference and Dense Semantic Correspondencecited by 53
- 2020Going to Extremes: Weakly Supervised Medical Image Segmentationcited by 38
- 2019Tag2Pix: Line Art Colorization Using Text Tag With SECat and Changing Losscited by 35
- 2020Bipartite Graph Reasoning GANs for Person Image Generationcited by 34
- 2018Sequential Attention GAN for Interactive Image Editingcited by 33
- 2018User-Guided Deep Anime Line Art Colorization with Conditional Adversarial Networkscited by 32
- 2019Coloring With Limited Data: Few-Shot Colorization via Memory-Augmented Networkscited by 32
- 2017Unsupervised Diverse Colorization via Generative Adversarial Networkscited by 30
- 2018FaceShop: Deep Sketch-based Face Image Editingcited by 24
- 2020MichiGAN: Multi-Input-Conditioned Hair Image Generation for Portrait Editingcited by 18
- 2019Constrained Generative Adversarial Networks for Interactive Image Generationcited by 10
- 2018Interactive Deep Colorization With Simultaneous Global and Local Inputscited by 5
- 2020A deep learning based interactive sketching system for fashion images designcited by 3
- 2020Localized Interactive Instance Segmentationcited by 1
Built on by
Citing papers per year: 2024: 1; 2025: 1; 2026: 1.
3 papers.