ABSTRACT
While the quality of face manipulation has been improved tremendously, the ability to control face components, e.g., eyebrows, is still limited. Although existing methods have realized component editing with user-provided geometry guidance, such as masks or sketches, their performance is largely dependent on the user's painting efforts. To address these issues, we propose Box-FaceS, a bidirectional method that can edit face components by simply translating and zooming the bounding boxes. This framework learns representations for every face component, independently, as well as a high-dimensional tensor capturing face outlines. To enable box-guided face editing, we develop a novel Box Adaptive Modulation (BAM) module for the generator, which first transforms component embeddings to style parameters and then modulates visual features inside a given box-like region on the face outlines. A cooperative learning scheme is proposed to impose independence between face outlines and component embeddings. As a result, it is flexible to determine the component style by its embedding, and to control its position and size by the provided bounding box. Box-FaceS also learns to transfer components between two faces while maintaining the consistency of image content. In particular, Box-FaceS can generate creative faces with reasonable exaggerations, requiring neither supervision nor complex spatial morphing operations. Through the comparisons with state-of-the-art methods, Box-FaceS shows its superiority in component editing, both qualitatively and quantitatively. To the best of our knowledge, Box-FaceS is the first approach that can freely edit the position and shape of the face components without editing the face masks or sketches. Our implementation is available at https://github.com/CMACH508/Box-FaceS.
Supplemental Material
Available for Download
- Rameen Abdal, Yipeng Qin, and Peter Wonka. 2019. Image2stylegan: How to embed images into the stylegan latent space?. In Proceedings of the IEEE international conference on computer vision. 4432--4441.Google ScholarCross Ref
- Rameen Abdal, Yipeng Qin, and Peter Wonka. 2020. Image2StyleGAN: How to Edit the Embedded Images?. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 8296--8305.Google ScholarCross Ref
- Rameen Abdal, Peihao Zhu, Niloy Mitra, and Peter Wonka. 2020. Styleflow: Attribute-conditioned exploration of stylegan-generated images using conditional continuous normalizing flows. arXiv e-prints (2020), arXiv-2008.Google Scholar
- David Bau, Jun-Yan Zhu, Hendrik Strobelt, Bolei Zhou, Joshua B. Tenenbaum, William T. Freeman, and Antonio Torralba. 2019. Visualizing and Understanding Generative Adversarial Networks. In International Conference on Learning Representations.Google Scholar
- Shu-Yu Chen, Wanchao Su, Lin Gao, Shihong Xia, and Hongbo Fu. 2020. Deep- FaceDrawing: Deep generation of face images from sketches. ACM Transactions on Graphics (TOG) 39, 4 (2020), 72--1.Google ScholarDigital Library
- Shu-Yu Chen, Wanchao Su, Lin Gao, Shihong Xia, and Hongbo Fu. 2020. Deep- FaceDrawing: Deep generation of face images from sketches. ACM Transactions on Graphics (TOG) 39, 4 (2020), 72-1.Google ScholarDigital Library
- Anton Cherepkov, Andrey Voynov, and Artem Babenko. 2021. Navigating the gan parameter space for semantic image editing. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 3671--3680.Google ScholarCross Ref
- Edo Collins, Raja Bala, Bob Price, and Sabine Susstrunk. 2020. Editing in style: Uncovering the local semantics of gans. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 5771--5780.Google ScholarCross Ref
- Qiyao Deng, Jie Cao, Yunfan Liu, Zhenhua Chai, Qi Li, and Zhenan Sun. 2020. Reference Guided Face Component Editing. In Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence, IJCAI 2020, Christian Bessiere (Ed.). ijcai.org, 502--508. https://doi.org/10.24963/ijcai.2020/70Google ScholarCross Ref
- Ian Goodfellow, Jean Pouget-Abadie, Mehdi Mirza, Bing Xu, David Warde-Farley, Sherjil Ozair, Aaron Courville, and Yoshua Bengio. 2014. Generative adversarial nets. Advances in neural information processing systems 27 (2014).Google Scholar
- Shuyang Gu, Jianmin Bao, Hao Yang, Dong Chen, Fang Wen, and Lu Yuan. 2019. Mask-guided portrait editing with conditional gans. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 3436--3445.Google ScholarCross Ref
- Kaiming He, Xiangyu Zhang, Shaoqing Ren, and Jian Sun. 2016. Deep residual learning for image recognition. In Proceedings of the IEEE conference on computer vision and pattern recognition. 770--778.Google ScholarCross Ref
- Martin Heusel, Hubert Ramsauer, Thomas Unterthiner, Bernhard Nessler, and Sepp Hochreiter. 2017. Gans trained by a two time-scale update rule converge to a local nash equilibrium. arXiv preprint arXiv:1706.08500 (2017).Google Scholar
- Wenjin Huang, Shikui Tu, and Lei Xu. 2019. Revisit lmser from a deep learning perspective. In International Conference on Intelligent Science and Big Data Engineering. Springer, 197--208.Google ScholarCross Ref
- Wenjing Huang, Shikui Tu, and Lei Xu. 2020. Deep CNN based Lmser and strengths of two built-in dualities. Neural Processing Letters (2020), 1--17.Google Scholar
- Wenjing Huang, Shikui Tu, and Lei Xu. 2022. IA-FaceS: A Bidirectional Method for Semantic Face Editing. https://doi.org/10.48550/ARXIV.2203.13097Google Scholar
- Erik HÃd'rkÃűnen, Aaron Hertzmann, Jaakko Lehtinen, and Sylvain Paris. 2020. GANSpace: Discovering Interpretable GAN Controls. In Proc. NeurIPS.Google Scholar
- Tero Karras, Timo Aila, Samuli Laine, and Jaakko Lehtinen. 2018. Progressive Growing of GANs for Improved Quality, Stability, and Variation. In International Conference on Learning Representations.Google Scholar
- Tero Karras, Miika Aittala, Janne Hellsten, Samuli Laine, Jaakko Lehtinen, and Timo Aila. 2020. Training generative adversarial networks with limited data. Advances in Neural Information Processing Systems 33 (2020), 12104--12114.Google Scholar
- Tero Karras, Samuli Laine, and Timo Aila. 2019. A style-based generator architecture for generative adversarial networks. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 4401--4410.Google ScholarCross Ref
- Tero Karras, Samuli Laine, Miika Aittala, Janne Hellsten, Jaakko Lehtinen, and Timo Aila. 2020. Analyzing and improving the image quality of stylegan. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 8110--8119.Google ScholarCross Ref
- Hyunsu Kim, Yunjey Choi, Junho Kim, Sungjoo Yoo, and Youngjung Uh. 2021. Exploiting Spatial Dimensions of Latent in GAN for Real-Time Image Editing. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 852--861.Google ScholarCross Ref
- Hyunsu Kim, Yunjey Choi, Junho Kim, Sungjoo Yoo, and Youngjung Uh. 2021. Exploiting Spatial Dimensions of Latent in GAN for Real-time Image Editing. https://doi.org/10.48550/ARXIV.2104.14754Google Scholar
- Diederik P Kingma and Jimmy Ba. 2014. Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014).Google Scholar
- Ranjay Krishna, Yuke Zhu, Oliver Groth, Justin Johnson, Kenji Hata, Joshua Kravitz, Stephanie Chen, Yannis Kalantidis, Li-Jia Li, David A Shamma, et al. 2017. Visual genome: Connecting language and vision using crowdsourced dense image annotations. International journal of computer vision 123, 1 (2017), 32--73.Google Scholar
- Cheng-Han Lee, Ziwei Liu, Lingyun Wu, and Ping Luo. 2020. MaskGAN: Towards Diverse and Interactive Facial Image Manipulation. In IEEE Conference on Computer Vision and Pattern Recognition (CVPR).Google Scholar
- Peiying Li, Shikui Tu, and Lei Xu. 2019. GAN flexible Lmser for super-resolution. In Proceedings of the 27th ACM International Conference on Multimedia. 756--764.Google ScholarDigital Library
- Wenbin Li, Wei Xiong, Haofu Liao, Jing Huo, Yang Gao, and Jiebo Luo. 2020. Carigan: Caricature generation through weakly paired adversarial learning. Neural Networks 132 (2020), 66--74.Google ScholarCross Ref
- Huan Ling, Karsten Kreis, Daiqing Li, Seung Wook Kim, Antonio Torralba, and Sanja Fidler. 2021. EditGAN: High-Precision Semantic Image Editing. Advances in Neural Information Processing Systems 34 (2021).Google Scholar
- Huan Ling, Karsten Kreis, Daiqing Li, Seung Wook Kim, Antonio Torralba, and Sanja Fidler. 2021. EditGAN: High-Precision Semantic Image Editing. Advances in Neural Information Processing Systems 34 (2021).Google Scholar
- Ziwei Liu, Ping Luo, XiaogangWang, and Xiaoou Tang. 2015. Deep Learning Face Attributes in the Wild. In Proceedings of International Conference on Computer Vision (ICCV).Google ScholarDigital Library
- Lars Mescheder, Andreas Geiger, and Sebastian Nowozin. 2018. Which training methods for GANs do actually converge?. In International conference on machine learning. PMLR, 3481--3490.Google Scholar
- Stanislav Pidhorskyi, Donald A Adjeroh, and Gianfranco Doretto. 2020. Adversarial latent autoencoders. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 14104--14113.Google ScholarCross Ref
- Wei Shen and Rujie Liu. 2017. Learning residual images for face attribute manipulation. In Proceedings of the IEEE conference on computer vision and pattern recognition. 4030--4038.Google ScholarCross Ref
- Yujun Shen, Jinjin Gu, Xiaoou Tang, and Bolei Zhou. 2020. Interpreting the latent space of gans for semantic face editing. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 9243--9252.Google ScholarCross Ref
- Yichun Shi, Debayan Deb, and Anil K Jain. 2019. Warpgan: Automatic caricature generation. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 10762--10771.Google ScholarCross Ref
- Karen Simonyan and Andrew Zisserman. 2015. Very Deep Convolutional Networks for Large-Scale Image Recognition. In International Conference on Learning Representations.Google Scholar
- Ting-Chun Wang, Ming-Yu Liu, Jun-Yan Zhu, Andrew Tao, Jan Kautz, and Bryan Catanzaro. 2018. High-resolution image synthesis and semantic manipulation with conditional gans. In Proceedings of the IEEE conference on computer vision and pattern recognition. 8798--8807.Google ScholarCross Ref
- Zhou Wang, Alan C Bovik, Hamid R Sheikh, and Eero P Simoncelli. 2004. Image quality assessment: from error visibility to structural similarity. IEEE transactions on image processing 13, 4 (2004), 600--612.Google ScholarDigital Library
- Zongze Wu, Dani Lischinski, and Eli Shechtman. 2021. Stylespace analysis: Disentangled controls for stylegan image generation. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 12863--12872.Google ScholarCross Ref
- Lei Xu. 1993. Least mean square error reconstruction principle for self-organizing neural-nets. Neural networks 6, 5 (1993), 627--648.Google Scholar
- Lei Xu. 2019. An overview and perspectives on bidirectional intelligence: Lmser duality, double IA harmony, and causal computation. IEEE/CAA Journal of Automatica Sinica 6, 4 (2019), 865--893. https://doi.org/10.1109/JAS.2019.1911603Google ScholarCross Ref
- Ceyuan Yang, Yujun Shen, and Bolei Zhou. 2021. Semantic hierarchy emerges in deep generative representations for scene synthesis. International Journal of Computer Vision 129, 5 (2021), 1451--1466.Google ScholarCross Ref
- Xu Yao, Alasdair Newson, Yann Gousseau, and Pierre Hellier. 2021. A latent transformer for disentangled face editing in images and videos. In Proceedings of the IEEE/CVF international conference on computer vision. 13789--13798.Google ScholarCross Ref
- Xu Yao, Alasdair Newson, Yann Gousseau, and Pierre Hellier. 2021. Learning non-linear disentangled editing for stylegan. In 2021 IEEE International Conference on Image Processing (ICIP). IEEE, 2418--2422.Google ScholarCross Ref
- Richard Zhang, Phillip Isola, Alexei A Efros, Eli Shechtman, and Oliver Wang. 2018. The unreasonable effectiveness of deep features as a perceptual metric. In Proceedings of the IEEE conference on computer vision and pattern recognition. 586--595.Google ScholarCross Ref
- Jiapeng Zhu, Yujun Shen, Deli Zhao, and Bolei Zhou. 2020. In-domain gan inversion for real image editing. In European Conference on Computer Vision. Springer, 592--608.Google ScholarDigital Library
- Peihao Zhu, Rameen Abdal, Yipeng Qin, and Peter Wonka. 2020. Sean: Image synthesis with semantic region-adaptive normalization. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 5104--5113.Google ScholarCross Ref
Index Terms
- Box-FaceS: A Bidirectional Method for Box-Guided Face Component Editing
Recommendations
Recognition of Faces Using Improved Principal Component Analysis
ICMLC '10: Proceedings of the 2010 Second International Conference on Machine Learning and ComputingFace recognition has been an important issue in computer vision and pattern recognition over the last several decades. While a human can recognize faces easily, automated face recognition remains a great challenge in computer-based automated recognition ...
Open-set face recognition across look-alike faces in real-world scenarios
The open-set problem is among the problems that have significantly changed the performance of face recognition algorithms in real-world scenarios. Open-set operates under the supposition that not all the probes have a pair in the gallery. Most face ...
Learning from Partially Occluded Faces
ICPRAM 2016: Proceedings of the 5th International Conference on Pattern Recognition Applications and MethodsAlthough face recognition methods in controlled environments have achieved high accuracy results, there
are still problems in real-life situations. Some of the challenges include changes in face expressions, pose,
lighting conditions or presence of ...
Comments