StyleGAN2 Distillation for Feed-Forward Image Manipulation

Viazovetskyi, Yuri; Ivashkin, Vladimir; Kashin, Evgeny

doi:10.1007/978-3-030-58542-6_11

Cited by 115 publications

(68 citation statements)

References 37 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, it uses auxiliary attribute classifiers, relies on large annotated datasets, and can generally not achieve the fine editing control of our EditGAN. Finally, we compare to (iv) StyleGAN2 Distillation 5 [82], which creates an alternative approach that does not require real image embeddings and also relies on an editing-vector model to create a training dataset.…”

Section: Quantitative Resultsmentioning

confidence: 99%

“…In Tab. 2, we also compare with StyleGAN2 Distillation [82], which achieves strong performance. However, StyleGAN2 Distillation relies on pre-trained classifiers, like InterfaceGAN, and only enables relatively high-level editing of image attributes for which large-scale annotations exit.…”

Section: Rotate Wheel Spokementioning

confidence: 99%

“…At inference time when performing editing, we use the same test image embeddings for the InterFaceGAN model as we use for our EditGAN model. As mentioned in the main paper, we also use StyleGAN2 Distillation [82] as baseline, for which we rely on the official codebase 10 and train a Pix2PixHD network for the smile edit using the default hyperparameters as provided in the paper [82]. We further show in Fig.…”

Section: B1 Smile Edit Benchmarkmentioning

confidence: 99%

See 2 more Smart Citations

EditGAN: High-Precision Semantic Image Editing

Ling¹,

Kreis²,

Li³

et al. 2021

Preprint

View full text Add to dashboard Cite

Generative adversarial networks (GANs) have recently found applications in image editing. However, most GAN-based image editing methods often require large-scale datasets with semantic segmentation annotations for training, only provide high level control, or merely interpolate between different images. Here, we propose EditGAN, a novel method for high-quality, high-precision semantic image editing, allowing users to edit images by modifying their highly detailed part segmentation masks, e.g., drawing a new mask for the headlight of a car. EditGAN builds on a GAN framework that jointly models images and their semantic segmentations [1, 2], requiring only a handful of labeled examples -making it a scalable tool for editing. Specifically, we embed an image into the GAN's latent space and perform conditional latent code optimization according to the segmentation edit, which effectively also modifies the image. To amortize optimization, we find "editing vectors" in latent space that realize the edits. The framework allows us to learn an arbitrary number of editing vectors, which can then be directly applied on other images at interactive rates. We experimentally show that EditGAN can manipulate images with an unprecedented level of detail and freedom, while preserving full image quality.We can also easily combine multiple edits and perform plausible edits beyond EditGAN's training data. We demonstrate EditGAN on a wide variety of image types and quantitatively outperform several previous editing methods on standard editing benchmark tasks. Project page: https://nv-tlabs.github.io/editGAN.

show abstract

Section: Quantitative Resultsmentioning

confidence: 99%

Section: Rotate Wheel Spokementioning

confidence: 99%

Section: B1 Smile Edit Benchmarkmentioning

confidence: 99%

See 1 more Smart Citation

EditGAN: High-Precision Semantic Image Editing

Ling¹,

Kreis²,

Li³

et al. 2021

Preprint

View full text Add to dashboard Cite

show abstract

“…Recently, Chen et al [12] proposed a pixel translation framework for high resolution facial image editing. Viazovetskyi et al [13] used generated high resolution images to train the pix2pixHD [14] for facial attribute manipulation. Latent Space Exploration.…”

Section: Related Workmentioning

confidence: 99%

Learning Non-Linear Disentangled Editing For Stylegan

Yao

Newson

Gousseau

et al. 2021

2021 IEEE International Conference on Image Processing (ICIP)

View full text Add to dashboard Cite

EyeglassesGray Hair Age Hairline Original Slender Smiling Wavy Hair Makeup Sequential disentangled attribute manipulation. We show in this example how to achieve realistic, controllable, disentangled face editing. From the original image (center), we propose two opposite editing directions where only one attribute is manipulated at a time. To the right: 'slender', 'smiling', 'wavy hair' and 'makeup' and to the left: 'receding hairline', 'age', 'gray hair' and 'eyeglasses'. All results are obtained at resolution 1024 2 .

show abstract

“…GAN-Encoders aims to find out w corresponding to the input X In , and w itself also has semantic sense [6]. It is meaningful in image manipulation [7,8,9], compression, restoration, editing and enhancement tasks.…”

Section: Introduction and Previous Workmentioning

confidence: 99%

Expressive And Compressive Gan Inversion Network

Xu¹,

Zhang²

2021

2021 IEEE International Conference on Image Processing (ICIP)

View full text Add to dashboard Cite

This paper presents a novel encoding framework for the generative adversarial network (GAN), named compressive GAN inverter (Comp-GI), which can effectively compress, restore, and edit the attributes of real-world images. In particular, Comp-GI first transforms the input image into the latent variable space of GAN through an encoder network and then manipulates the latent code vector to enable various semantic image editing operations. StyleGAN [1] and its improved version StyleGANv2 [2] are adopted as the default GANs for image generation. Experiments on benchmark datasets FFHQ demonstrate that the proposed Comp-GI achieves better restoration performance with finer details and fewer artifacts than existing state-of-the-art GAN-inversion methods.

show abstract

StyleGAN2 Distillation for Feed-Forward Image Manipulation

Cited by 115 publications

References 37 publications

EditGAN: High-Precision Semantic Image Editing

EditGAN: High-Precision Semantic Image Editing

Learning Non-Linear Disentangled Editing For Stylegan

Expressive And Compressive Gan Inversion Network

Contact Info

Product

Resources

About