English
Related papers

Related papers: RefineStyle: Dynamic Convolution Refinement for St…

200 papers

GAN inversion and editing via StyleGAN maps an input image into the embedding spaces ($\mathcal{W}$, $\mathcal{W^+}$, and $\mathcal{F}$) to simultaneously maintain image fidelity and meaningful manipulation. From latent space $\mathcal{W}$…

Computer Vision and Pattern Recognition · Computer Science 2023-03-28 Hongyu Liu , Yibing Song , Qifeng Chen

Image inpainting, which refers to the synthesis of missing regions in an image, can help restore occluded or degraded areas and also serve as a precursor task for self-supervision. The current state-of-the-art models for image inpainting…

Computer Vision and Pattern Recognition · Computer Science 2023-07-04 Pranav Jeevan , Dharshan Sampath Kumar , Amit Sethi

StyleGAN models show editing capabilities via their semantically interpretable latent organizations which require successful GAN inversion methods to edit real images. Many works have been proposed for inverting images into StyleGAN's…

Computer Vision and Pattern Recognition · Computer Science 2023-12-19 Ahmet Burak Yildirim , Hamza Pehlivan , Aysegul Dundar

The task of manipulating real image attributes through StyleGAN inversion has been extensively researched. This process involves searching latent variables from a well-trained StyleGAN generator that can synthesize a real image, modifying…

Computer Vision and Pattern Recognition · Computer Science 2024-06-18 Denis Bobkov , Vadim Titov , Aibek Alanov , Dmitry Vetrov

Generative Adversarial Networks (GANs) with style-based generators (e.g. StyleGAN) successfully enable semantic control over image synthesis, and recent studies have also revealed that interpretable image translations could be obtained by…

Computer Vision and Pattern Recognition · Computer Science 2020-11-20 Yunfan Liu , Qi Li , Zhenan Sun , Tieniu Tan

Dynamic convolution learns a linear mixture of n static kernels weighted with their input-dependent attentions, demonstrating superior performance than normal convolution. However, it increases the number of convolutional parameters by n…

Computer Vision and Pattern Recognition · Computer Science 2024-06-13 Chao Li , Anbang Yao

Recent work has shown that a variety of semantics emerge in the latent space of Generative Adversarial Networks (GANs) when being trained to synthesize images. However, it is difficult to use these learned semantics for real image editing.…

Computer Vision and Pattern Recognition · Computer Science 2020-07-17 Jiapeng Zhu , Yujun Shen , Deli Zhao , Bolei Zhou

Recent inversion methods have shown that real images can be inverted into StyleGAN's latent space and numerous edits can be achieved on those images thanks to the semantically rich feature representations of well-trained GAN models.…

Computer Vision and Pattern Recognition · Computer Science 2023-07-28 Ahmet Burak Yildirim , Hamza Pehlivan , Bahri Batuhan Bilecen , Aysegul Dundar

GAN inversion aims to invert an input image into the latent space of a pre-trained GAN. Despite the recent advances in GAN inversion, there remain challenges to mitigate the tradeoff between distortion and editability, i.e. reconstructing…

Computer Vision and Pattern Recognition · Computer Science 2022-07-20 Xudong Mao , Liujuan Cao , Aurele T. Gnanha , Zhenguo Yang , Qing Li , Rongrong Ji

Despite remarkable recent progress on both unconditional and conditional image synthesis, it remains a long-standing problem to learn generative models that are capable of synthesizing realistic and sharp images from reconfigurable spatial…

Computer Vision and Pattern Recognition · Computer Science 2019-08-21 Wei Sun , Tianfu Wu

In image denoising networks, feature scaling is widely used to enlarge the receptive field size and reduce computational costs. This practice, however, also leads to the loss of high-frequency information and fails to consider within-scale…

Computer Vision and Pattern Recognition · Computer Science 2023-04-04 Hao Shen , Zhong-Qiu Zhao , Wandi Zhang

Convolutional neural networks (CNNs) have achieved state-of-the-art results on many visual recognition tasks. However, current CNN models still exhibit a poor ability to be invariant to spatial transformations of images. Intuitively, with…

Computer Vision and Pattern Recognition · Computer Science 2019-12-04 Xu Shen , Xinmei Tian , Anfeng He , Shaoyan Sun , Dacheng Tao

The introduction of high-quality image generation models, particularly the StyleGAN family, provides a powerful tool to synthesize and manipulate images. However, existing models are built upon high-quality (HQ) data as desired outputs,…

Computer Vision and Pattern Recognition · Computer Science 2022-12-08 Dat Viet Thanh Nguyen , Phong Tran The , Tan M. Dinh , Cuong Pham , Anh Tuan Tran

Dynamic convolution learns a linear mixture of $n$ static kernels weighted with their sample-dependent attentions, demonstrating superior performance compared to normal convolution. However, existing designs are parameter-inefficient: they…

Computer Vision and Pattern Recognition · Computer Science 2023-08-17 Chao Li , Anbang Yao

We propose Image2StyleGAN++, a flexible image editing framework with many applications. Our framework extends the recent Image2StyleGAN in three ways. First, we introduce noise optimization as a complement to the $W^+$ latent space…

Computer Vision and Pattern Recognition · Computer Science 2020-08-10 Rameen Abdal , Yipeng Qin , Peter Wonka

Pixel-level fine-grained image editing remains an open challenge. Previous works fail to achieve an ideal trade-off between control granularity and inference speed. They either fail to achieve pixel-level fine-grained control, or their…

Computer Vision and Pattern Recognition · Computer Science 2024-07-29 Pengxiang Cai , Zhiwei Liu , Guibo Zhu , Yunfang Niu , Jinqiao Wang

Filters in convolutional networks are typically parameterized in a pixel basis, that does not take prior knowledge about the visual world into account. We investigate the generalized notion of frames designed with image properties in mind,…

Computer Vision and Pattern Recognition · Computer Science 2017-07-20 Jörn-Henrik Jacobsen , Bert de Brabandere , Arnold W. M. Smeulders

With the remarkable recent progress on learning deep generative models, it becomes increasingly interesting to develop models for controllable image synthesis from reconfigurable inputs. This paper focuses on a recent emerged task,…

Computer Vision and Pattern Recognition · Computer Science 2021-03-30 Wei Sun , Tianfu Wu

Text-to-image diffusion models have remarkably excelled in producing diverse, high-quality, and photo-realistic images. This advancement has spurred a growing interest in incorporating specific identities into generated content. Most…

Computer Vision and Pattern Recognition · Computer Science 2023-11-30 Xiaoming Li , Xinyu Hou , Chen Change Loy

Domain adaptation of GANs is a problem of fine-tuning GAN models pretrained on a large dataset (e.g. StyleGAN) to a specific domain with few samples (e.g. painting faces, sketches, etc.). While there are many methods that tackle this…

Computer Vision and Pattern Recognition · Computer Science 2023-09-13 Aibek Alanov , Vadim Titov , Maksim Nakhodnov , Dmitry Vetrov