GAN

2022-11-22 更新

Shape, Pose, and Appearance from a Single Image via Bootstrapped Radiance Field Inversion

Authors:Dario Pavllo, David Joseph Tan, Marie-Julie Rakotosaona, Federico Tombari

Neural Radiance Fields (NeRF) coupled with GANs represent a promising direction in the area of 3D reconstruction from a single view, owing to their ability to efficiently model arbitrary topologies. Recent work in this area, however, has mostly focused on synthetic datasets where exact ground-truth poses are known, and has overlooked pose estimation, which is important for certain downstream applications such as augmented reality (AR) and robotics. We introduce a principled end-to-end reconstruction framework for natural images, where accurate ground-truth poses are not available. Our approach recovers an SDF-parameterized 3D shape, pose, and appearance from a single image of an object, without exploiting multiple views during training. More specifically, we leverage an unconditional 3D-aware generator, to which we apply a hybrid inversion scheme where a model produces a first guess of the solution which is then refined via optimization. Our framework can de-render an image in as few as 10 steps, enabling its use in practical scenarios. We demonstrate state-of-the-art results on a variety of real and synthetic benchmarks.
PDF

点此查看论文截图

Face Swapping as A Simple Arithmetic Operation

Authors:Truong Vu, Kien Do, Khang Nguyen, Khoat Than

We propose a novel high-fidelity face swapping method called “Arithmetic Face Swapping” (AFS) that explicitly disentangles the intermediate latent space W+ of a pretrained StyleGAN into the “identity” and “style” subspaces so that a latent code in W+ is the sum of an “identity” code and a “style” code in the corresponding subspaces. Via our disentanglement, face swapping (FS) can be regarded as a simple arithmetic operation in W+, i.e., the summation of a source “identity” code and a target “style” code. This makes AFS more intuitive and elegant than other FS methods. In addition, our method can generalize over the standard face swapping to support other interesting operations, e.g., combining the identity of one source with styles of multiple targets and vice versa. We implement our identity-style disentanglement by learning a neural network that maps a latent code to a “style” code. We provide a condition for this network which theoretically guarantees identity preservation of the source face even after a sequence of face swapping operations. Extensive experiments demonstrate the advantage of our method over state-of-the-art FS methods in producing high-quality swapped faces.
PDF

点此查看论文截图

Scale-free and Task-agnostic Attack: Generating Photo-realistic Adversarial Patterns with Patch Quilting Generator

Authors:Xiangbo Gao, Cheng Luo, Qinliang Lin, Weicheng Xie, Minmin Liu, Linlin Shen, Keerthy Kusumam, Siyang Song

\noindent Traditional L_p norm-restricted image attack algorithms suffer from poor transferability to black box scenarios and poor robustness to defense algorithms. Recent CNN generator-based attack approaches can synthesize unrestricted and semantically meaningful entities to the image, which is shown to be transferable and robust. However, such methods attack images by either synthesizing local adversarial entities, which are only suitable for attacking specific contents or performing global attacks, which are only applicable to a specific image scale. In this paper, we propose a novel Patch Quilting Generative Adversarial Networks (PQ-GAN) to learn the first scale-free CNN generator that can be applied to attack images with arbitrary scales for various computer vision tasks. The principal investigation on transferability of the generated adversarial examples, robustness to defense frameworks, and visual quality assessment show that the proposed PQG-based attack framework outperforms the other nine state-of-the-art adversarial attack approaches when attacking the neural networks trained on two standard evaluation datasets (i.e., ImageNet and CityScapes).
PDF

点此查看论文截图

Audio-visual video face hallucination with frequency supervision and cross modality support by speech based lip reading loss

Authors:Shailza Sharma, Abhinav Dhall, Vinay Kumar, Vivek Singh Bawa

Recently, there has been numerous breakthroughs in face hallucination tasks. However, the task remains rather challenging in videos in comparison to the images due to inherent consistency issues. The presence of extra temporal dimension in video face hallucination makes it non-trivial to learn the facial motion through out the sequence. In order to learn these fine spatio-temporal motion details, we propose a novel cross-modal audio-visual Video Face Hallucination Generative Adversarial Network (VFH-GAN). The architecture exploits the semantic correlation of between the movement of the facial structure and the associated speech signal. Another major issue in present video based approaches is the presence of blurriness around the key facial regions such as mouth and lips - where spatial displacement is much higher in comparison to other areas. The proposed approach explicitly defines a lip reading loss to learn the fine grain motion in these facial areas. During training, GANs have potential to fit frequencies from low to high, which leads to miss the hard to synthesize frequencies. Therefore, to add salient frequency features to the network we add a frequency based loss function. The visual and the quantitative comparison with state-of-the-art shows a significant improvement in performance and efficacy.
PDF

点此查看论文截图

Real-World Image Super Resolution via Unsupervised Bi-directional Cycle Domain Transfer Learning based Generative Adversarial Network

Authors:Xiang Wang, Yimin Yang, Zhichang Guo, Zhili Zhou, Yu Liu, Qixiang Pang, Shan Du

Deep Convolutional Neural Networks (DCNNs) have exhibited impressive performance on image super-resolution tasks. However, these deep learning-based super-resolution methods perform poorly in real-world super-resolution tasks, where the paired high-resolution and low-resolution images are unavailable and the low-resolution images are degraded by complicated and unknown kernels. To break these limitations, we propose the Unsupervised Bi-directional Cycle Domain Transfer Learning-based Generative Adversarial Network (UBCDTL-GAN), which consists of an Unsupervised Bi-directional Cycle Domain Transfer Network (UBCDTN) and the Semantic Encoder guided Super Resolution Network (SESRN). First, the UBCDTN is able to produce an approximated real-like LR image through transferring the LR image from an artificially degraded domain to the real-world LR image domain. Second, the SESRN has the ability to super-resolve the approximated real-like LR image to a photo-realistic HR image. Extensive experiments on unpaired real-world image benchmark datasets demonstrate that the proposed method achieves superior performance compared to state-of-the-art methods.
PDF 12 pages, 5 figures,3 tables. This work is submitted to IEEE Transactions on Systems, Man, and Cybernetics: Systems (2022). It’s under review by IEEE Transactions on Systems, Man, and Cybernetics: Systems for now

点此查看论文截图

Next3D: Generative Neural Texture Rasterization for 3D-Aware Head Avatars

Authors:Jingxiang Sun, Xuan Wang, Lizhen Wang, Xiaoyu Li, Yong Zhang, Hongwen Zhang, Yebin Liu

3D-aware generative adversarial networks (GANs) synthesize high-fidelity and multi-view-consistent facial images using only collections of single-view 2D imagery. Towards fine-grained control over facial attributes, recent efforts incorporate 3D Morphable Face Model (3DMM) to describe deformation in generative radiance fields either explicitly or implicitly. Explicit methods provide fine-grained expression control but cannot handle topological changes caused by hair and accessories, while implicit ones can model varied topologies but have limited generalization caused by the unconstrained deformation fields. We propose a novel 3D GAN framework for unsupervised learning of generative, high-quality and 3D-consistent facial avatars from unstructured 2D images. To achieve both deformation accuracy and topological flexibility, we propose a 3D representation called Generative Texture-Rasterized Tri-planes. The proposed representation learns Generative Neural Textures on top of parametric mesh templates and then projects them into three orthogonal-viewed feature planes through rasterization, forming a tri-plane feature representation for volume rendering. In this way, we combine both fine-grained expression control of mesh-guided explicit deformation and the flexibility of implicit volumetric representation. We further propose specific modules for modeling mouth interior which is not taken into account by 3DMM. Our method demonstrates state-of-the-art 3D-aware synthesis quality and animation ability through extensive experiments. Furthermore, serving as 3D prior, our animatable 3D representation boosts multiple applications including one-shot facial avatars and 3D-aware stylization.
PDF Project page: https://mrtornado24.github.io/Next3D/

点此查看论文截图

Delving StyleGAN Inversion for Image Editing: A Foundation Latent Space Viewpoint

Authors:Hongyu Liu, Yibing Song, Qifeng Chen

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 $\mathcal{W}$ to extended latent space $\mathcal{W^+}$ to feature space $\mathcal{F}$ in StyleGAN, the editability of GAN inversion decreases while its reconstruction quality increases. Recent GAN inversion methods typically explore $\mathcal{W^+}$ and $\mathcal{F}$ rather than $\mathcal{W}$ to improve reconstruction fidelity while maintaining editability. As $\mathcal{W^+}$ and $\mathcal{F}$ are derived from $\mathcal{W}$ that is essentially the foundation latent space of StyleGAN, these GAN inversion methods focusing on $\mathcal{W^+}$ and $\mathcal{F}$ spaces could be improved by stepping back to $\mathcal{W}$. In this work, we propose to first obtain the precise latent code in foundation latent space $\mathcal{W}$. We introduce contrastive learning to align $\mathcal{W}$ and the image space for precise latent code discovery. %The obtaining process is by using contrastive learning to align $\mathcal{W}$ and the image space. Then, we leverage a cross-attention encoder to transform the obtained latent code in $\mathcal{W}$ into $\mathcal{W^+}$ and $\mathcal{F}$, accordingly. Our experiments show that our exploration of the foundation latent space $\mathcal{W}$ improves the representation ability of latent codes in $\mathcal{W^+}$ and features in $\mathcal{F}$, which yields state-of-the-art reconstruction fidelity and editability results on the standard benchmarks. Project page: \url{https://github.com/KumapowerLIU/CLCAE}.
PDF

点此查看论文截图

GlassesGAN: Eyewear Personalization using Synthetic Appearance Discovery and Targeted Subspace Modeling

Authors:Richard Plesh, Peter Peer, Vitomir Štruc

We present GlassesGAN, a novel image editing framework for custom design of glasses, that sets a new standard in terms of image quality, edit realism, and continuous multi-style edit capability. To facilitate the editing process with GlassesGAN, we propose a Targeted Subspace Modelling (TSM) procedure that, based on a novel mechanism for (synthetic) appearance discovery in the latent space of a pre-trained GAN generator, constructs an eyeglasses-specific (latent) subspace that the editing framework can utilize. Additionally, we also introduce an appearance-constrained subspace initialization (SI) technique that centers the latent representation of the given input image in the well-defined part of the constructed subspace to improve the reliability of the learned edits. We test GlassesGAN on two (diverse) high-resolution datasets (CelebA-HQ and SiblingsDB-HQf) and compare it to three state-of-the-art competitors, i.e., InterfaceGAN, GANSpace, and MaskGAN. The reported results show that GlassesGAN convincingly outperforms all competing techniques, while offering additional functionality (e.g., fine-grained multi-style editing) not available with any of the competitors. The source code will be made freely available.
PDF 18 pages, 18 figures, 3 tables

点此查看论文截图

Differentiable Gaussianization Layers for Inverse Problems Regularized by Deep Generative Models

Authors:Dongzhuo Li

Deep generative models such as GANs, normalizing flows, and diffusion models are powerful regularizers for inverse problems. They exhibit great potential for helping reduce ill-posedness and attain high-quality results. However, the latent tensors of such deep generative models can fall out of the desired high-dimensional standard Gaussian distribution during an inversion process, particularly in the presence of data noise and inaccurate forward models. In such cases, deep generative models are ineffective in attaining high-fidelity solutions. To address this issue, we propose to reparameterize and Gaussianize the latent tensors using novel differentiable data-dependent layers wherein custom operators are defined by solving optimization problems. These proposed layers constrain inverse problems to obtain high-fidelity in-distribution solutions. We tested and validated our technique on three inversion tasks: compressive-sensing MRI, image deblurring, and eikonal tomography (a nonlinear PDE-constrained inverse problem), using two representative deep generative models: StyleGAN2 and Glow, and achieved state-of-the-art performance in terms of accuracy and consistency.
PDF 33 pages, 21 figures, 11 tables

点此查看论文截图

Deep Composite Face Image Attacks: Generation, Vulnerability and Detection

Authors:Jag Mohan Singh, Raghavendra Ramachandra

Face manipulation attacks have drawn the attention of biometric researchers because of their vulnerability to Face Recognition Systems (FRS). This paper proposes a novel scheme to generate Composite Face Image Attacks (CFIA) based on the Generative Adversarial Networks (GANs). Given the face images from contributory data subjects, the proposed CFIA method will independently generate the segmented facial attributes, then blend them using transparent masks to generate the CFIA samples. { The primary motivation for CFIA is to utilize deep learning to generate facial attribute-based composite attacks, which has been explored relatively less in the current literature.} We generate $14$ different combinations of facial attributes resulting in $14$ unique CFIA samples for each pair of contributory data subjects. Extensive experiments are carried out on our newly generated CFIA dataset consisting of 1000 unique identities with 2000 bona fide samples and 14000 CFIA samples, thus resulting in an overall 16000 face image samples. We perform a sequence of experiments to benchmark the vulnerability of CFIA to automatic FRS (based on both deep-learning and commercial-off-the-shelf (COTS). We introduced a new metric named Generalized Morphing Attack Potential (GMAP) to benchmark the vulnerability effectively. Additional experiments are performed to compute the perceptual quality of the generated CFIA samples. Finally, the CFIA detection performance is presented using three different Face Morphing Attack Detection (MAD) algorithms. The proposed CFIA method indicates good perceptual quality based on the obtained results. Further, { FRS is vulnerable to CFIA} (much higher than SOTA), making it difficult to detect by human observers and automatic detection algorithms. Lastly, we performed experiments to detect the CFIA samples using three different detection techniques automatically.
PDF

点此查看论文截图

IC3D: Image-Conditioned 3D Diffusion for Shape Generation

Authors:Cristian Sbrolli, Paolo Cudrano, Matteo Frosi, Matteo Matteucci

In the last years, Denoising Diffusion Probabilistic Models (DDPMs) obtained state-of-the-art results in many generative tasks, outperforming GANs and other classes of generative models. In particular, they reached impressive results in various image generation sub-tasks, among which conditional generation tasks such as text-guided image synthesis. Given the success of DDPMs in 2D generation, they have more recently been applied to 3D shape generation, outperforming previous approaches and reaching state-of-the-art results. However, 3D data pose additional challenges, such as the choice of the 3D representation, which impacts design choices and model efficiency. While reaching state-of-the-art results in generation quality, existing 3D DDPM works make little or no use of guidance, mainly being unconditional or class-conditional. In this paper, we present IC3D, the first Image-Conditioned 3D Diffusion model that generates 3D shapes by image guidance. It is also the first 3D DDPM model that adopts voxels as a 3D representation. To guide our DDPM, we present and leverage CISP (Contrastive Image-Shape Pre-training), a model jointly embedding images and shapes by contrastive pre-training, inspired by text-to-image DDPM works. Our generative diffusion model outperforms the state-of-the-art in 3D generation quality and diversity. Furthermore, we show that our generated shapes are preferred by human evaluators to a SoTA single-view 3D reconstruction model in terms of quality and coherence to the query image by running a side-by-side human evaluation.
PDF

点此查看论文截图