We present En3D, an enhanced generative scheme for sculpting high-quality 3D human avatars. Unlike previous works that rely on scarce 3D datasets or limited 2D collections with imbalanced viewing angles and imprecise pose priors, our approach aims to develop a zero-shot 3D generative scheme capable of producing visually realistic, geometrically accurate and content-wise diverse 3D humans without relying on pre-existing 3D or 2D assets. To address this challenge, we introduce a meticulously crafted workflow that implements accurate physical modeling to learn the enhanced 3D generative model from synthetic 2D data. During inference, we integrate optimization modules to bridge the gap between realistic appearances and coarse 3D shapes. Specifically, En3D comprises three modules: a 3D generator that accurately models generalizable 3D humans with realistic appearance from synthesized balanced, diverse, and structured human images; a geometry sculptor that enhances shape quality using multi-view normal constraints for intricate human anatomy; and a texturing module that disentangles explicit texture maps with fidelity and editability, leveraging semantical UV partitioning and a differentiable rasterizer. Experimental results show that our approach significantly outperforms prior works in terms of image quality, geometry accuracy and content diversity. We also showcase the applicability of our generated avatars for animation and editing, as well as the scalability of our approach for content-style free adaptation.
This paper presents a 3D generative model that uses diffusion models to automatically generate 3D digital avatars represented as neural radiance fields. A significant challenge in generating such avatars is that the memory and processing costs in 3D are prohibitive for producing the rich details required for high-quality avatars. To tackle this problem we propose the roll-out diffusion network (Rodin), which represents a neural radiance field as multiple 2D feature maps and rolls out these maps into a single 2D feature plane within which we perform 3D-aware diffusion. The Rodin model brings th…
The University of Hong Kong（香港大学）；University of Oxford（牛津大学）；ByteDance（字节跳动）
Recent text-to-image generation models have shown promising results in generating high-fidelity photo-realistic images. Though the results are astonishing to human eyes, how applicable these generated images are for recognition tasks remains under-explored. In this work, we extensively study whether and how synthetic images generated from state-of-the-art text-to-image generation models can be used for image recognition tasks, and focus on two perspectives: synthetic data for improving classification models in data-scarce settings (i.e. zero-shot and few-shot), and synthetic data for large-sca…
Synthetic images rendered from 3D CAD models are useful for augmenting training data for object recognition algorithms. However, the generated images are non-photorealistic and do not match real image statistics. This leads to a large domain discrepancy, causing models trained on synthetic data to perform poorly on real domains. Recent work has shown the great potential of deep convolutional neural networks to generate realistic images, but has not utilized generative models to address synthetic-to-real domain adaptation. In this work, we propose a Deep Generative Correlation Alignment Network…
Object detection and recognition has been an ongoing research topic for a long time in the field of computer vision. Even in robotics, detecting the state of an object by a robot still remains a challenging task. Also, collecting data for each possible state is also not feasible. In this literature, we use a deep convolutional neural network with SVM as a classifier to help with recognizing the state of a cooking object. We also study how a generative adversarial network can be used for synthetic data augmentation and improving the classification accuracy. The main motivation behind this work …
Currently there is strong interest in data-driven approaches to medical image classification. However, medical imaging data is scarce, expensive, and fraught with legal concerns regarding patient privacy. Typical consent forms only allow for patient data to be used in medical journals or education, meaning the majority of medical data is inaccessible for general public research. We propose a novel, two-stage pipeline for generating synthetic medical images from a pair of generative adversarial networks, tested in practice on retinal fundi images. We develop a hierarchical generation process to…
Generative Adversarial Neural Networks (GANs) are applied to the synthetic generation of prostate lesion MRI images. GANs have been applied to a variety of natural images, is shown show that the same techniques can be used in the medical domain to create realistic looking synthetic lesion images. 16mm x 16mm patches are extracted from 330 MRI scans from the SPIE ProstateX Challenge 2016 and used to train a Deep Convolutional Generative Adversarial Neural Network (DCGAN) utilizing cutting edge techniques. Synthetic outputs are compared to real images and the implicit latent representations indu…
In this paper we report on improved part segmentation performance using convolutional neural networks to reduce the dependency on the large amount of manually annotated empirical images. This was achieved by optimising the visual realism of synthetic agricultural images.In Part I, a cycle consistent generative adversarial network was applied to synthetic and empirical images with the objective to generate more realistic synthetic images by translating them to the empirical domain. We first hypothesise and confirm that plant part image features such as color and texture become more similar to t…
Generative adversarial networks (GANs) are able to generate high resolution photo-realistic images of objects that "do not exist." These synthetic images are rather difficult to detect as fake. However, the manner in which these generative models are trained hints at a potential for information leakage from the supplied training data, especially in the context of synthetic faces. This paper presents experiments suggesting that identity information in face images can flow from the training corpus into synthetic samples without any adversarial actions when building or using the existing model. T…
West Virginia University（西弗吉尼亚大学）；IIIT Delhi（印度德里信息技术研究所）
Reliability and accuracy of iris biometric modality has prompted its large-scale deployment for critical applications such as border control and national ID projects. The extensive growth of iris recognition systems has raised apprehensions about susceptibility of these systems to various attacks. In the past, researchers have examined the impact of various iris presentation attacks such as textured contact lenses and print attacks. In this research, we present a novel presentation attack using deep learning based synthetic iris generation. Utilizing the generative capability of deep convoluti…
Improving the Effectiveness of Deep Generative Data
Bosch Center for Artificial Intelligence（博世人工智能中心）；Institute of Industrial Manufacturing and Management IFF, University of Stuttgart（斯图加特大学工业制造与管理研究所）；Fraunhofer Institute for Manufacturing Engineering and Automation (IPA)（弗劳恩霍夫制造工程与自动化研究所）
In this work, we propose a novel Cyclic Image Translation Generative Adversarial Network (CIT-GAN) for multi-domain style transfer. To facilitate this, we introduce a Styling Network that has the capability to learn style characteristics of each domain represented in the training dataset. The Styling Network helps the generator to drive the translation of images from a source domain to a reference domain and generate synthetic images with style characteristics of the reference domain. The learned style characteristics for each domain depend on both the style loss and domain classification loss…
SynDoc: A Hybrid Discriminative-Generative Framework for Enhancing Synthetic Domain-Adaptive Document Key Information Extraction
The University of Western Australia（西澳大学）；The University of Melbourne（墨尔本大学）；The University of Sydney（悉尼大学）；Weill Cornell Medicine, Cornell University（韦尔·科恩医学中心，康奈尔大学）
To synthesize high-quality person images with arbitrary poses is challenging. In this paper, we propose a novel Multi-scale Conditional Generative Adversarial Networks (MsCGAN), aiming to convert the input conditional person image to a synthetic image of any given target pose, whose appearance and the texture are consistent with the input image. MsCGAN is a multi-scale adversarial network consisting of two generators and two discriminators. One generator transforms the conditional person image into a coarse image of the target pose globally, and the other is to enhance the detailed quality of …
Pre-training with 3D Synthetic Data: Learning 3D Point Cloud Instance Segmentation from 3D Synthetic Scenes
TICO-AIST Cooperative Research Laboratory for Advanced Logistics (ALlab)（TICO-AIST高级物流合作研究实验室（ALlab））；National Institute of Advanced Industrial Science and Technology (AIST)（日本国立先进工业科学技术研究院（AIST））；Visual Geometry Group, University of Oxford（牛津大学视觉几何组）
Indian Institute of Technology Kharagpur（印度理工学院卡拉格普尔分校）
Autonomous driving is one of the most recent topics of interest which is aimed at replicating human driving behavior keeping in mind the safety issues. We approach the problem of learning synthetic driving using generative neural networks. The main idea is to make a controller trainer network using images plus key press data to mimic human learning. We used the architecture of a stable GAN to make predictions between driving scenes using key presses. We train our model on one video game (Road Rash) and tested the accuracy and compared it by running the model on other maps in Road Rash to deter…
In this work, we present an application of domain randomization and generative adversarial networks (GAN) to train a near real-time object detector for industrial electric parts, entirely in a simulated environment. Large scale availability of labelled real world data is typically rare and difficult to obtain in many industrial settings. As such here, only a few hundred of unlabelled real images are used to train a Cyclic-GAN network, in combination with various degree of domain randomization procedures. We demonstrate that this enables robust translation of synthetic images to the real world …
Mythic Inc.（Mythic公司）；Freeus, LLC.（Freeus有限责任公司）；University of Rochester（罗切斯特大学）
Deep neural networks can form high-level hierarchical representations of input data. Various researchers have demonstrated that these representations can be used to enable a variety of useful applications. However, such representations are typically based on the statistics within the data, and may not conform with the semantic representation that may be necessitated by the application. Conditional models are typically used to overcome this challenge, but they require large annotated datasets which are difficult to come by and costly to create. In this paper, we show that semantically-aligned r…
Metadata-Conditioned Generative Models to Synthesize Anatomically-Plausible 3D Brain MRIs
Stanford University（斯坦福大学）；University of Missouri（密苏里大学）；Missouri Institute of Mental Health（密苏里精神卫生研究所）；Weill Cornell Medicine（威尔康奈尔医学院）；SRI International（SRI国际研究所）
Ford Motor Company（福特汽车公司）；Michigan State University（密歇根州立大学）
The evaluation of synthetic micro-structure images is an emerging problem as machine learning and materials science research have evolved together. Typical state of the art methods in evaluating synthetic images from generative models have relied on the Fréchet Inception Distance. However, this and other similar methods, are limited in the materials domain due to both the unique features that characterize physically accurate micro-structures and limited dataset sizes. In this study we evaluate a variety of methods on scanning electron microscope (SEM) images of graphene-reinforced polyurethane…
University of Maryland, Baltimore County（马里兰大学巴尔的摩分校）；National Institutes of Health Clinical Center（美国国立卫生研究院临床中心）；Networking Health；OpenKneck Inc（OpenKneck公司）
We present a novel conditional Generative Adversarial Network (cGAN) architecture that is capable of generating 3D Computed Tomography scans in voxels from noisy and/or pixelated approximations and with the potential to generate full synthetic 3D scan volumes. We believe conditional cGAN to be a tractable approach to generate 3D CT volumes, even though the problem of generating full resolution deep fakes is presently impractical due to GPU memory limitations. We present results for autoencoder, denoising, and depixelating tasks which are trained and tested on two novel COVID19 CT datasets. Our…
SkinGenBench: Generative Model and Preprocessing Effects for Synthetic Dermoscopic Augmentation in Melanoma Diagnosis
Alliance School of Advanced Computing, Alliance University, India（印度联盟大学高级计算学院）；Department of Computer Science and Communication, Østfold University College, 1783 Halden, Norway（挪威东福尔大学学院计算机科学与传播系）；Department of Dentistry and Oral Health, Aarhus University, 8000 Aarhus, Denmark（丹麦奥胡斯大学牙科与口腔健康系）
The difficulty in obtaining labeled data relevant to a given task is among the most common and well-known practical obstacles to applying deep learning techniques to new or even slightly modified domains. The data volumes required by the current generation of supervised learning algorithms typically far exceed what a human needs to learn and complete a given task. We investigate ways to expand a given labeled corpus of remote sensed imagery into a larger corpus using Generative Adversarial Networks (GANs). We then measure how these additional synthetic data affect supervised machine learning p…
NVIDIA Corporation（英伟达公司）；MGH & BWH Center for Clinical Data Science（麻省总医院与布列根和妇女医院临床数据科学中心）；Mayo Clinic（妙佑医疗国际）
Data diversity is critical to success when training deep learning models. Medical imaging data sets are often imbalanced as pathologic findings are generally rare, which introduces significant challenges when training deep learning models. In this work, we propose a method to generate synthetic abnormal MRI images with brain tumors by training a generative adversarial network using two publicly available data sets of brain MRI. We demonstrate two unique benefits that the synthetic images provide. First, we illustrate improved performance on tumor segmentation by leveraging the synthetic images…
Improving watermelon (Citrullus lanatus) disease classification with generative artificial intelligence (GenAI)-based synthetic and real-field images via a custom EfficientNetV2-L model
University of Catania（卡塔尼亚大学）；iCTLab Spinoff of University of Catania（卡塔尼亚大学iCTLab衍生公司）；Banca d’Italia（意大利银行）
Most recent style-transfer techniques based on generative architectures are able to obtain synthetic multimedia contents, or commonly called deepfakes, with almost no artifacts. Researchers already demonstrated that synthetic images contain patterns that can determine not only if it is a deepfake but also the generative architecture employed to create the image data itself. These traces can be exploited to study problems that have never been addressed in the context of deepfakes. To this aim, in this paper a first approach to investigate the image ballistics on deepfake images subject to style…
Problem: There is a lack of big data for the training of deep learning models in medicine, characterized by the time cost of data collection and privacy concerns. Generative adversarial networks (GANs) offer both the potential to generate new data, as well as to use this newly generated data, without inclusion of patients' real data, for downstream applications. Approach: A series of GANs were trained and applied for a downstream computer vision spine radiograph abnormality classification task. Separate classifiers were trained with either access or no access to the original imaging. Trained G…
