Surrogate Gradient Field for Latent Space Manipulation
Minjun Li, Yanghua Jin, Huachun Zhu
2021年份
2顶会引用
摘要
Figure 1 . Our Surrogate Gradient Field (SGF) can edit images with diverse modalities of control by manipulating the latent codes of GANs. In the first row, we adjust the facial attributes of a person's photo. In the second row, we use natural language sentences to alter the color and the shape of a generated flower. In the last row, we edit keypoints of a generated anime character to modify head poses. We use StyleGAN2 [20] to generate the images above.
问问这篇 Paper
智能体会读完全文。
Lune 把这篇 Paper 索引到了每一个公式,引用它的顶会 Paper 也一样。你提问,回答直接引用原文。
引用它的顶会 Paper2
- Learning Disentangled Representation by Exploiting Pretrained Generative Models: A Contrastive Learning ViewXuanchi Ren, Tao Yang, Yuwang Wang, Wenjun ZengICLR 2022 · 被引用 54 次
- Householder Projector for Unsupervised Latent Semantics DiscoveryYue Song, Jichao Zhang, Nicu Sebe, Wei WangICCV 2023 · 被引用 9 次
它引用的顶会 Paper9
- Image2StyleGAN: How to Embed Images Into the StyleGAN Latent Space?Rameen Abdal, Yipeng Qin, Peter WonkaICCV 2019 · 被引用 1,195 次
- GANSpace: Discovering Interpretable GAN ControlsErik Härkönen, Aaron Hertzmann, Jaakko Lehtinen, Sylvain ParisNeurIPS 2020 · 被引用 1,049 次
- Differentiable Augmentation for Data-Efficient GAN TrainingShengyu Zhao, Zhijian Liu, Ji Lin, Jun-Yan Zhu 等NeurIPS 2020 · 被引用 707 次
- Unsupervised Discovery of Interpretable Directions in the GAN Latent SpaceAndrey Voynov, Artem BabenkoICML 2020 · 被引用 459 次
- On the "steerability" of generative adversarial networksAli Jahanian, Lucy Chai, Phillip IsolaICLR 2020 · 被引用 421 次
相关 Paper
- Conceptual and Hierarchical Latent Space Decomposition for Face EditingSavas Özkan, Mete Özay, Tom RobinsonICCV 2023 · 被引用 3 次
- A Latent Transformer for Disentangled Face Editing in Images and VideosXu Yao, Alasdair Newson, Yann Gousseau, Pierre HellierICCV 2021 · 被引用 97 次
- Latent Transformations via NeuralODEs for GAN-based Image EditingValentin Khrulkov, Leyla Mirvakhabova, Ivan V. Oseledets, Artem BabenkoICCV 2021 · 被引用 15 次
- Navigating the GAN Parameter Space for Semantic Image EditingAnton Cherepkov, Andrey Voynov, Artem BabenkoCVPR 2021
- Everything is There in Latent Space: Attribute Editing and Attribute Style Manipulation by StyleGAN Latent Space ExplorationRishubh Parihar, Ankit Dhiman, Tejan Karmali, Venkatesh Babu R.ACM MM 2022 · 被引用 21 次
