2024-01-05 更新
E4S: Fine-grained Face Swapping via Editing With Regional GAN Inversion
Authors:Maomao Li, Ge Yuan, Cairong Wang, Zhian Liu, Yong Zhang, Yongwei Nie, Jue Wang, Dong Xu
This paper proposes a novel approach to face swapping from the perspective of fine-grained facial editing, dubbed “editing for swapping” (E4S). The traditional face swapping methods rely on global feature extraction and often fail to preserve the source identity. In contrast, our framework proposes a Regional GAN Inversion (RGI) method, which allows the explicit disentanglement of shape and texture. Specifically, our E4S performs face swapping in the latent space of a pretrained StyleGAN, where a multi-scale mask-guided encoder is applied to project the texture of each facial component into regional style codes and a mask-guided injection module then manipulates feature maps with the style codes. Based on this disentanglement, face swapping can be simplified as style and mask swapping. Besides, since reconstructing the source face in the target image may lead to disharmony lighting, we propose to train a re-coloring network to make the swapped face maintain the lighting condition on the target face. Further, to deal with the potential mismatch area during mask exchange, we designed a face inpainting network as post-processing. The extensive comparisons with state-of-the-art methods demonstrate that our E4S outperforms existing methods in preserving texture, shape, and lighting. Our implementation is available at https://github.com/e4s2023/E4S2023.
PDF Project Page: https://e4s2023.github.io/ ;. arXiv admin note: text overlap with arXiv:2211.14068
点此查看论文截图
Latents2Semantics: Leveraging the Latent Space of Generative Models for Localized Style Manipulation of Face Images
Authors:Snehal Singh Tomar, A. N. Rajagopalan
With the metaverse slowly becoming a reality and given the rapid pace of developments toward the creation of digital humans, the need for a principled style editing pipeline for human faces is bound to increase manifold. We cater to this need by introducing the Latents2Semantics Autoencoder (L2SAE), a Generative Autoencoder model that facilitates highly localized editing of style attributes of several Regions of Interest (ROIs) in face images. The L2SAE learns separate latent representations for encoded images’ structure and style information. Thus, allowing for structure-preserving style editing of the chosen ROIs. The encoded structure representation is a multichannel 2D tensor with reduced spatial dimensions, which captures both local and global structure properties. The style representation is a 1D tensor that captures global style attributes. In our framework, we slice the structure representation to build strong and disentangled correspondences with different ROIs. Consequentially, style editing of the chosen ROIs amounts to a simple combination of (a) the ROI-mask generated from the sliced structure representation and (b) the decoded image with global style changes, generated from the manipulated (using Gaussian noise) global style and unchanged structure tensor. Style editing sans additional human supervision is a significant win over SOTA style editing pipelines because most existing works require additional human effort (supervision) post-training for attributing semantic meaning to style edits. We also do away with iterative-optimization-based inversion or determining controllable latent directions post-training, which requires additional computationally expensive operations. We provide qualitative and quantitative results for the same over multiple applications, such as selective style editing and swapping using test images sampled from several datasets.
PDF Accepted as an oral paper at the AAAI-24 Workshop on AI for Digital Human
点此查看论文截图
From Covert Hiding to Visual Editing: Robust Generative Video Steganography
Authors:Xueying Mao, Xiaoxiao Hu, Wanli Peng, Zhenliang Gan, Qichao Ying, Zhenxing Qian, Sheng Li, Xinpeng Zhang
Traditional video steganography methods are based on modifying the covert space for embedding, whereas we propose an innovative approach that embeds secret message within semantic feature for steganography during the video editing process. Although existing traditional video steganography methods display a certain level of security and embedding capacity, they lack adequate robustness against common distortions in online social networks (OSNs). In this paper, we introduce an end-to-end robust generative video steganography network (RoGVS), which achieves visual editing by modifying semantic feature of videos to embed secret message. We employ face-swapping scenario to showcase the visual editing effects. We first design a secret message embedding module to adaptively hide secret message into the semantic feature of videos. Extensive experiments display that the proposed RoGVS method applied to facial video datasets demonstrate its superiority over existing video and image steganography techniques in terms of both robustness and capacity.
PDF Under Review
点此查看论文截图
Towards a Simultaneous and Granular Identity-Expression Control in Personalized Face Generation
Authors:Renshuai Liu, Bowen Ma, Wei Zhang, Zhipeng Hu, Changjie Fan, Tangjie Lv, Yu Ding, Xuan Cheng
In human-centric content generation, the pre-trained text-to-image models struggle to produce user-wanted portrait images, which retain the identity of individuals while exhibiting diverse expressions. This paper introduces our efforts towards personalized face generation. To this end, we propose a novel multi-modal face generation framework, capable of simultaneous identity-expression control and more fine-grained expression synthesis. Our expression control is so sophisticated that it can be specialized by the fine-grained emotional vocabulary. We devise a novel diffusion model that can undertake the task of simultaneously face swapping and reenactment. Due to the entanglement of identity and expression, it’s nontrivial to separately and precisely control them in one framework, thus has not been explored yet. To overcome this, we propose several innovative designs in the conditional diffusion model, including balancing identity and expression encoder, improved midpoint sampling, and explicitly background conditioning. Extensive experiments have demonstrated the controllability and scalability of the proposed framework, in comparison with state-of-the-art text-to-image, face swapping, and face reenactment methods.
PDF
点此查看论文截图