Zobrazeno 1 - 10
of 217
pro vyhledávání: '"Kolkin, A."'
We address the challenges of precise image inversion and disentangled image editing in the context of few-step diffusion models. We introduce an encoder based iterative inversion technique. The inversion network is conditioned on the input image and
Externí odkaz:
http://arxiv.org/abs/2408.08332
Autor:
Ham, Cusuh, Fisher, Matthew, Hays, James, Kolkin, Nicholas, Liu, Yuchen, Zhang, Richard, Hinz, Tobias
We present personalized residuals and localized attention-guided sampling for efficient concept-driven generation using text-to-image diffusion models. Our method first represents concepts by freezing the weights of a pretrained text-conditioned diff
Externí odkaz:
http://arxiv.org/abs/2405.12978
Generative models excel at mimicking real scenes, suggesting they might inherently encode important intrinsic scene properties. In this paper, we aim to explore the following key questions: (1) What intrinsic knowledge do generative models like GANs,
Externí odkaz:
http://arxiv.org/abs/2311.17137
Autor:
He, Xingzhe, Cao, Zhiwen, Kolkin, Nicholas, Yu, Lantao, Wan, Kun, Rhodin, Helge, Kalarot, Ratheesh
Large text-to-image models have revolutionized the ability to generate imagery using natural language. However, particularly unique or personal visual concepts, such as pets and furniture, will not be captured by the original model. This has led to i
Externí odkaz:
http://arxiv.org/abs/2311.04315
Autor:
Ruta, Dan, Tarrés, Gemma Canet, Gilbert, Andrew, Shechtman, Eli, Kolkin, Nicholas, Collomosse, John
Neural Style Transfer (NST) is the field of study applying neural techniques to modify the artistic appearance of a content image to match the style of a reference style image. Traditionally, NST methods have focused on texture-based image edits, aff
Externí odkaz:
http://arxiv.org/abs/2307.04157
Style transfer is the task of reproducing the semantic contents of a source image in the artistic style of a second target image. In this paper, we present NeAT, a new state-of-the art feed-forward style transfer method. We re-formulate feed-forward
Externí odkaz:
http://arxiv.org/abs/2304.05139
We propose Fast text2StyleGAN, a natural language interface that adapts pre-trained GANs for text-guided human face synthesis. Leveraging the recent advances in Contrastive Language-Image Pre-training (CLIP), no text data is required during training.
Externí odkaz:
http://arxiv.org/abs/2209.03953
We present a method for transferring the artistic features of an arbitrary style image to a 3D scene. Previous methods that perform 3D stylization on point clouds or meshes are sensitive to geometric reconstruction errors for complex real-world scene
Externí odkaz:
http://arxiv.org/abs/2206.06360
Autor:
Kolkin, Nicholas, Kucera, Michal, Paris, Sylvain, Sykora, Daniel, Shechtman, Eli, Shakhnarovich, Greg
We propose Neural Neighbor Style Transfer (NNST), a pipeline that offers state-of-the-art quality, generalization, and competitive efficiency for artistic style transfer. Our approach is based on explicitly replacing neural features extracted from th
Externí odkaz:
http://arxiv.org/abs/2203.13215
Multi-modal domain translation typically refers to synthesizing a novel image that inherits certain localized attributes from a 'content' image (e.g. layout, semantics, or geometry), and inherits everything else (e.g. texture, lighting, sometimes eve
Externí odkaz:
http://arxiv.org/abs/2110.06443