2024-01-05 更新
What You See is What You GAN: Rendering Every Pixel for High-Fidelity Geometry in 3D GANs
Authors:Alex Trevithick, Matthew Chan, Towaki Takikawa, Umar Iqbal, Shalini De Mello, Manmohan Chandraker, Ravi Ramamoorthi, Koki Nagano
3D-aware Generative Adversarial Networks (GANs) have shown remarkable progress in learning to generate multi-view-consistent images and 3D geometries of scenes from collections of 2D images via neural volume rendering. Yet, the significant memory and computational costs of dense sampling in volume rendering have forced 3D GANs to adopt patch-based training or employ low-resolution rendering with post-processing 2D super resolution, which sacrifices multiview consistency and the quality of resolved geometry. Consequently, 3D GANs have not yet been able to fully resolve the rich 3D geometry present in 2D images. In this work, we propose techniques to scale neural volume rendering to the much higher resolution of native 2D images, thereby resolving fine-grained 3D geometry with unprecedented detail. Our approach employs learning-based samplers for accelerating neural rendering for 3D GAN training using up to 5 times fewer depth samples. This enables us to explicitly “render every pixel” of the full-resolution image during training and inference without post-processing superresolution in 2D. Together with our strategy to learn high-quality surface geometry, our method synthesizes high-resolution 3D geometry and strictly view-consistent images while maintaining image quality on par with baselines relying on post-processing super resolution. We demonstrate state-of-the-art 3D gemetric quality on FFHQ and AFHQ, setting a new standard for unsupervised learning of 3D shapes in 3D GANs.
PDF See our project page: https://research.nvidia.com/labs/nxp/wysiwyg/
点此查看论文截图
2024-01-05 更新
EGAIN: Extended GAn INversion
Authors:Wassim Kabbani, Marcel Grimmer, Christoph Busch
Generative Adversarial Networks (GANs) have witnessed significant advances in recent years, generating increasingly higher quality images, which are non-distinguishable from real ones. Recent GANs have proven to encode features in a disentangled latent space, enabling precise control over various semantic attributes of the generated facial images such as pose, illumination, or gender. GAN inversion, which is projecting images into the latent space of a GAN, opens the door for the manipulation of facial semantics of real face images. This is useful for numerous applications such as evaluating the performance of face recognition systems. In this work, EGAIN, an architecture for constructing GAN inversion models, is presented. This architecture explicitly addresses some of the shortcomings in previous GAN inversion models. A specific model with the same name, egain, based on this architecture is also proposed, demonstrating superior reconstruction quality over state-of-the-art models, and illustrating the validity of the EGAIN architecture.
PDF
点此查看论文截图
Scalable Face Image Coding via StyleGAN Prior: Towards Compression for Human-Machine Collaborative Vision
Authors:Qi Mao, Chongyu Wang, Meng Wang, Shiqi Wang, Ruijie Chen, Libiao Jin, Siwei Ma
The accelerated proliferation of visual content and the rapid development of machine vision technologies bring significant challenges in delivering visual data on a gigantic scale, which shall be effectively represented to satisfy both human and machine requirements. In this work, we investigate how hierarchical representations derived from the advanced generative prior facilitate constructing an efficient scalable coding paradigm for human-machine collaborative vision. Our key insight is that by exploiting the StyleGAN prior, we can learn three-layered representations encoding hierarchical semantics, which are elaborately designed into the basic, middle, and enhanced layers, supporting machine intelligence and human visual perception in a progressive fashion. With the aim of achieving efficient compression, we propose the layer-wise scalable entropy transformer to reduce the redundancy between layers. Based on the multi-task scalable rate-distortion objective, the proposed scheme is jointly optimized to achieve optimal machine analysis performance, human perception experience, and compression ratio. We validate the proposed paradigm’s feasibility in face image compression. Extensive qualitative and quantitative experimental results demonstrate the superiority of the proposed paradigm over the latest compression standard Versatile Video Coding (VVC) in terms of both machine analysis as well as human perception at extremely low bitrates ($<0.01$ bpp), offering new insights for human-machine collaborative compression.
PDF Accepted by IEEE TIP
点此查看论文截图
MuLA-GAN: Multi-Level Attention GAN for Enhanced Underwater Visibility
Authors:Ahsan Baidar Bakht, Zikai Jia, Muhayy ud Din, Waseem Akram, Lyes Saad Soud, Lakmal Seneviratne, Defu Lin, Shaoming He, Irfan Hussain
The underwater environment presents unique challenges, including color distortions, reduced contrast, and blurriness, hindering accurate analysis. In this work, we introduce MuLA-GAN, a novel approach that leverages the synergistic power of Generative Adversarial Networks (GANs) and Multi-Level Attention mechanisms for comprehensive underwater image enhancement. The integration of Multi-Level Attention within the GAN architecture significantly enhances the model’s capacity to learn discriminative features crucial for precise image restoration. By selectively focusing on relevant spatial and multi-level features, our model excels in capturing and preserving intricate details in underwater imagery, essential for various applications. Extensive qualitative and quantitative analyses on diverse datasets, including UIEB test dataset, UIEB challenge dataset, U45, and UCCS dataset, highlight the superior performance of MuLA-GAN compared to existing state-of-the-art methods. Experimental evaluations on a specialized dataset tailored for bio-fouling and aquaculture applications demonstrate the model’s robustness in challenging environmental conditions. On the UIEB test dataset, MuLA-GAN achieves exceptional PSNR (25.59) and SSIM (0.893) scores, surpassing Water-Net, the second-best model, with scores of 24.36 and 0.885, respectively. This work not only addresses a significant research gap in underwater image enhancement but also underscores the pivotal role of Multi-Level Attention in enhancing GANs, providing a novel and comprehensive framework for restoring underwater image quality.
PDF
点此查看论文截图
DiffusionGAN3D: Boosting Text-guided 3D Generation and Domain Adaption by Combining 3D GANs and Diffusion Priors
Authors:Biwen Lei, Kai Yu, Mengyang Feng, Miaomiao Cui, Xuansong Xie
Text-guided domain adaption and generation of 3D-aware portraits find many applications in various fields. However, due to the lack of training data and the challenges in handling the high variety of geometry and appearance, the existing methods for these tasks suffer from issues like inflexibility, instability, and low fidelity. In this paper, we propose a novel framework DiffusionGAN3D, which boosts text-guided 3D domain adaption and generation by combining 3D GANs and diffusion priors. Specifically, we integrate the pre-trained 3D generative models (e.g., EG3D) and text-to-image diffusion models. The former provides a strong foundation for stable and high-quality avatar generation from text. And the diffusion models in turn offer powerful priors and guide the 3D generator finetuning with informative direction to achieve flexible and efficient text-guided domain adaption. To enhance the diversity in domain adaption and the generation capability in text-to-avatar, we introduce the relative distance loss and case-specific learnable triplane respectively. Besides, we design a progressive texture refinement module to improve the texture quality for both tasks above. Extensive experiments demonstrate that the proposed framework achieves excellent results in both domain adaption and text-to-avatar tasks, outperforming existing methods in terms of generation quality and efficiency. The project homepage is at https://younglbw.github.io/DiffusionGAN3D-homepage/.
PDF
点此查看论文截图
EFHQ: Multi-purpose ExtremePose-Face-HQ dataset
Authors:Trung Tuan Dao, Duc Hong Vu, Cuong Pham, Anh Tran
The existing facial datasets, while having plentiful images at near frontal views, lack images with extreme head poses, leading to the downgraded performance of deep learning models when dealing with profile or pitched faces. This work aims to address this gap by introducing a novel dataset named Extreme Pose Face High-Quality Dataset (EFHQ), which includes a maximum of 450k high-quality images of faces at extreme poses. To produce such a massive dataset, we utilize a novel and meticulous dataset processing pipeline to curate two publicly available datasets, VFHQ and CelebV-HQ, which contain many high-resolution face videos captured in various settings. Our dataset can complement existing datasets on various facial-related tasks, such as facial synthesis with 2D/3D-aware GAN, diffusion-based text-to-image face generation, and face reenactment. Specifically, training with EFHQ helps models generalize well across diverse poses, significantly improving performance in scenarios involving extreme views, confirmed by extensive experiments. Additionally, we utilize EFHQ to define a challenging cross-view face verification benchmark, in which the performance of SOTA face recognition models drops 5-37% compared to frontal-to-frontal scenarios, aiming to stimulate studies on face recognition under severe pose conditions in the wild.
PDF Project Page: https://bomcon123456.github.io/efhq/
点此查看论文截图
Distance Guided Generative Adversarial Network for Explainable Binary Classifications
Authors:Xiangyu Xiong, Yue Sun, Xiaohong Liu, Wei Ke, Chan-Tong Lam, Jiangang Chen, Mingfeng Jiang, Mingwei Wang, Hui Xie, Tong Tong, Qinquan Gao, Hao Chen, Tao Tan
Despite the potential benefits of data augmentation for mitigating the data insufficiency, traditional augmentation methods primarily rely on the prior intra-domain knowledge. On the other hand, advanced generative adversarial networks (GANs) generate inter-domain samples with limited variety. These previous methods make limited contributions to describing the decision boundaries for binary classification. In this paper, we propose a distance guided GAN (DisGAN) which controls the variation degrees of generated samples in the hyperplane space. Specifically, we instantiate the idea of DisGAN by combining two ways. The first way is vertical distance GAN (VerDisGAN) where the inter-domain generation is conditioned on the vertical distances. The second way is horizontal distance GAN (HorDisGAN) where the intra-domain generation is conditioned on the horizontal distances. Furthermore, VerDisGAN can produce the class-specific regions by mapping the source images to the hyperplane. Experimental results show that DisGAN consistently outperforms the GAN-based augmentation methods with explainable binary classification. The proposed method can apply to different classification architectures and has potential to extend to multi-class classification.
PDF 12 pages, 8 figures. This work has been submitted to the IEEE TNNLS for possible publication. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media
点此查看论文截图
Is It Possible to Backdoor Face Forgery Detection with Natural Triggers?
Authors:Xiaoxuan Han, Songlin Yang, Wei Wang, Ziwen He, Jing Dong
Deep neural networks have significantly improved the performance of face forgery detection models in discriminating Artificial Intelligent Generated Content (AIGC). However, their security is significantly threatened by the injection of triggers during model training (i.e., backdoor attacks). Although existing backdoor defenses and manual data selection can mitigate those using human-eye-sensitive triggers, such as patches or adversarial noises, the more challenging natural backdoor triggers remain insufficiently researched. To further investigate natural triggers, we propose a novel analysis-by-synthesis backdoor attack against face forgery detection models, which embeds natural triggers in the latent space. We thoroughly study such backdoor vulnerability from two perspectives: (1) Model Discrimination (Optimization-Based Trigger): we adopt a substitute detection model and find the trigger by minimizing the cross-entropy loss; (2) Data Distribution (Custom Trigger): we manipulate the uncommon facial attributes in the long-tailed distribution to generate poisoned samples without the supervision from detection models. Furthermore, to completely evaluate the detection models towards the latest AIGC, we utilize both state-of-the-art StyleGAN and Stable Diffusion for trigger generation. Finally, these backdoor triggers introduce specific semantic features to the generated poisoned samples (e.g., skin textures and smile), which are more natural and robust. Extensive experiments show that our method is superior from three levels: (1) Attack Success Rate: ours achieves a high attack success rate (over 99%) and incurs a small model accuracy drop (below 0.2%) with a low poisoning rate (less than 3%); (2) Backdoor Defense: ours shows better robust performance when faced with existing backdoor defense methods; (3) Human Inspection: ours is less human-eye-sensitive from a comprehensive user study.
PDF
点此查看论文截图