相关参考文献
注意：仅列出部分参考文献，下载原文获取全部文献信息。
Proceedings Paper
Computer Science, Artificial Intelligence
Eric R. Chan et al.
Summary: In this work, a hybrid explicit-implicit network architecture is introduced to improve the computational efficiency and image quality of 3D GANs, allowing for unsupervised generation of high-quality multi-view-consistent images and 3D shapes.
2022 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2022)
(2022)
Proceedings Paper
Computer Science, Artificial Intelligence
Kunhee Kim et al.
Summary: Current image-to-image translation methods have limitations in controlling the output domain and interpolating between different domains. In order to address these issues, a style-aware discriminator is proposed to guide the generator, which achieved better results than current methods in experiments on multiple datasets.
2022 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2022)
(2022)
Proceedings Paper
Computer Science, Artificial Intelligence
Minsu Ko et al.
Summary: This paper proposes a regularization technique for improving GAN-based image-to-image translation by enforcing point-wise consistency of overlapping regions between patches during training. The experiment shows that this dense consistency regularization substantially improves performance on various image-to-image translation scenarios and can also be combined with instance-level regularization methods for additional gains. Furthermore, the proposed model is effective in capturing domain-specific characteristics with limited training data.
2022 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2022)
(2022)
Proceedings Paper
Computer Science, Artificial Intelligence
Yang Xue et al.
Summary: 3D-aware generative models have shown that introducing 3D information can lead to more controllable image generation. We propose GIRAFFE HD, a high-resolution 3D-aware generative model that inherits all the controllable features of GIRAFFE while generating high-quality, high-resolution images. The key idea is to leverage a style-based neural renderer to independently generate and stitch together foreground and background, resulting in coherent final images. We demonstrate state-of-the-art 3D controllable high-resolution image generation on multiple natural image datasets.
2022 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2022)
(2022)
Proceedings Paper
Computer Science, Artificial Intelligence
Shuai Yang et al.
Summary: Unsupervised image-to-image translation is challenging without paired data. This work proposes a novel framework that leverages pre-trained class-conditional GANs to learn content correspondences across different domains, improving the quality and applicability of the translation algorithm.
2022 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2022)
(2022)
Proceedings Paper
Computer Science, Artificial Intelligence
Xuanmeng Zhang et al.
Summary: This study aims to generate high-quality images with multi-view consistency by learning a 3D representation. To overcome the challenge of lacking geometry constraints in existing approaches, Multi-View Consistent Generative Adversarial Networks (MVCGAN) are proposed for joint optimization using 3D geometry information.
2022 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2022)
(2022)
Proceedings Paper
Computer Science, Artificial Intelligence
Ayush Tewari et al.
Summary: This paper proposes a 3D GAN model that can learn a disentangled model of objects from monocular observations. The model can separate the geometry and appearance variations in the scene, and achieve this using a non-rigid deformable scene formulation. Additionally, it improves the disentanglement between the 3D scene and the camera viewpoints using a pose regularization loss, and enables editing of real images through embedding them into the model's latent space.
2022 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2022)
(2022)
Proceedings Paper
Computer Science, Artificial Intelligence
Yu Deng et al.
Summary: The study aims to generate 3D-consistent images with controllable camera poses through 3D-aware image generative modeling. A novel approach is proposed to regulate point sampling and radiance field learning on 2D manifolds, addressing the limitations in handling fine details and stable training in existing generators.
2022 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR)
(2022)
Proceedings Paper
Computer Science, Artificial Intelligence
Xuning Shao et al.
Summary: This study proposes a discriminator architecture for unsupervised image-to-image translation that focuses on statistical features and stabilizes the network through distribution matching of key statistical features at multiple scales. By simplifying constraints on the generator, it allows for shape deformation and fine detail enhancement, outperforming existing state-of-the-art models in challenging applications.
2021 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV 2021)
(2021)
Proceedings Paper
Computer Science, Artificial Intelligence
Kyungjune Baek et al.
Summary: This paper introduces a truly unsupervised image-to-image translation model (TUNIT) that can be trained without paired images or domain labels. Experimental results show that the model performs comparably or even better than the set-level supervised model, generalizes well on various datasets, and is robust against hyperparameter choices. Additionally, TUNIT can easily be extended to semi-supervised learning with a small amount of labeled data.
2021 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV 2021)
(2021)
Proceedings Paper
Computer Science, Artificial Intelligence
Somi Jeong et al.
Summary: The study proposes a novel framework for instance-level image-to-image translation, addressing the issue of existing methods failing to handle images with multiple disparate objects by introducing a class-aware memory network. Experimental results demonstrate that the model outperforms recent instance-level methods and achieves state-of-the-art performance.
2021 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION, CVPR 2021
(2021)
Proceedings Paper
Computer Science, Artificial Intelligence
Yahui Liu et al.
Summary: This paper proposes a new training protocol and evaluation metric to help translation networks learn a smooth and disentangled latent style space, which significantly boosts the quality of generated images and the graduality of the interpolations.
2021 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION, CVPR 2021
(2021)
Proceedings Paper
Computer Science, Artificial Intelligence
Kangning Liu et al.
Summary: The UVIT model is an unsupervised video-to-video translation model that achieves style-consistent and realistic video translation results by decomposing style-content and propagating inter-frame information through bidirectional RNN. By training in a self-supervised manner with video interpolation loss, it can generate spatio-temporal consistent, multimodal translated videos.
2021 IEEE WINTER CONFERENCE ON APPLICATIONS OF COMPUTER VISION (WACV 2021)
(2021)
Article
Computer Science, Artificial Intelligence
Hsin-Ying Lee et al.
INTERNATIONAL JOURNAL OF COMPUTER VISION
(2020)
Proceedings Paper
Computer Science, Artificial Intelligence
Yaxing Wang et al.
2020 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR)
(2020)
Article
Computer Science, Artificial Intelligence
Wenjing Wang et al.
IEEE TRANSACTIONS ON IMAGE PROCESSING
(2020)
Proceedings Paper
Computer Science, Interdisciplinary Applications
Yaxing Wang et al.
PROCEEDINGS OF THE 27TH ACM INTERNATIONAL CONFERENCE ON MULTIMEDIA (MM'19)
(2019)
Proceedings Paper
Computer Science, Interdisciplinary Applications
Yang Chen et al.
PROCEEDINGS OF THE 27TH ACM INTERNATIONAL CONFERENCE ON MULTIMEDIA (MM'19)
(2019)
Proceedings Paper
Computer Science, Artificial Intelligence
Phillip Isola et al.
30TH IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2017)
(2017)
Proceedings Paper
Computer Science, Artificial Intelligence
Matheus Gadelha et al.
PROCEEDINGS 2017 INTERNATIONAL CONFERENCE ON 3D VISION (3DV)
(2017)
