尽管最近在基于文本提示的所谓“冷启动”生成方面取得了进展，但它们对数据和计算资源的需求，以及围绕知识产权和隐私问题的模糊性，对其效用提出了某些反驳。一个有趣且相对未被探索的替代方案是引入基于单个样本的无条件合成，这催生了有趣的生成应用。在本文中，我们专注于单样本动作生成，更具体地说，是加速生成对抗网络（GAN）的训练时间。具体而言，我们通过仔细退火防止模式崩溃的损失函数权重，解决了使用小批量训练时 GAN 的均衡崩溃挑战。此外，我们在生成器和判别器模型中执行统计分析，以识别训练阶段之间的相关性并实现迁移学习。与原始 GAN 架构和单样本扩散模型相比，我们改进的 GAN 在 Mixamo 基准上实现了具有竞争力的质量和多样性，同时训练时间比前者快 6.8 倍，比后者快 1.75 倍。最后，我们展示了我们改进的 GAN 能够通过单次前向传递混合和组合动作。项目页面可在 https://moverseai.github.io/single-shot 获取。
英文摘要：
Despite the recent advances in the so-called "cold start" generation from text prompts, their needs in data and computing resources, as well as the ambiguities around intellectual property and privacy concerns pose certain counterarguments for their utility. An interesting and relatively unexplored alternative has been the introduction of unconditional synthesis from a single sample, which has led to interesting generative applications. In this paper we focus on single-shot motion generation and more specifically on accelerating the training time of a Generative Adversarial Network (GAN). In particular, we tackle the challenge of GAN's equilibrium collapse when using mini-batch training by carefully annealing the weights of the loss functions that prevent mode collapse. Additionally, we perform statistical analysis in the generator and discriminator models to identify correlations between training stages and enable transfer learning. Our improved GAN achieves competitive quality and diversity on the Mixamo benchmark when compared to the original GAN architecture and a single-shot diffusion model, while being up to x6.8 faster in training time from the former and x1.75 from the latter. Finally, we demonstrate the ability of our improved GAN to mix and compose motion with a single forward pass. Project page available at https://moverseai.github.io/single-shot.
Bosch Center for Artificial Intelligence（博世人工智能中心）；University of Tübingen（图宾根大学）；University of Bonn（波恩大学）
Joint synthesis of images and segmentation masks with generative adversarial networks (GANs) is promising to reduce the effort needed for collecting image data with pixel-wise annotations. However, to learn high-fidelity image-mask synthesis, existing GAN approaches first need a pre-training phase requiring large amounts of image data, which limits their utilization in restricted image domains. In this work, we take a step to reduce this limitation, introducing the task of one-shot image-mask synthesis. We aim to generate diverse images and their segmentation masks given only a single labelled…
Video-to-video synthesis (vid2vid) aims at converting an input semantic video, such as videos of human poses or segmentation masks, to an output photorealistic video. While the state-of-the-art of vid2vid has advanced significantly, existing approaches share two major limitations. First, they are data-hungry. Numerous images of a target human subject or a scene are required for training. Second, a learned model has limited generalization capability. A pose-to-human vid2vid model can only synthesize poses of the single person in the training set. It does not generalize to other humans that are …
Samsung AI Center（三星人工智能中心）；Skolkovo Institute of Science and Technology（斯科尔科沃科学技术研究院）；University of Cambridge（剑桥大学）
We propose a neural rendering-based system that creates head avatars from a single photograph. Our approach models a person's appearance by decomposing it into two layers. The first layer is a pose-dependent coarse image that is synthesized by a small neural network. The second layer is defined by a pose-independent texture image that contains high-frequency details. The texture image is generated offline, warped and added to the coarse image to ensure a high effective resolution of synthesized head views. We compare our system to analogous state-of-the-art systems in terms of visual quality a…
Wangxuan Institute of Computer Technology, Peking University（北京大学王选计算机研究所）；Peking University（北京大学）
Automatic generation of high-quality Chinese fonts from a few online training samples is a challenging task, especially when the amount of samples is very small. Existing few-shot font generation methods can only synthesize low-resolution glyph images that often possess incorrect topological structures or/and incomplete strokes. To address the problem, this paper proposes FontTransformer, a novel few-shot learning model, for high-resolution Chinese glyph image synthesis by using stacked Transformers. The key idea is to apply the parallel Transformer to avoid the accumulation of prediction erro…
Training Generative Adversarial Networks (GAN) on high-fidelity images usually requires large-scale GPU-clusters and a vast number of training images. In this paper, we study the few-shot image synthesis task for GAN with minimum computing cost. We propose a light-weight GAN structure that gains superior quality on 1024*1024 resolution. Notably, the model converges from scratch with just a few hours of training on a single RTX-2080 GPU, and has a consistent performance, even with less than 100 training samples. Two technique designs constitute our work, a skip-layer channel-wise excitation mod…
In this work, we propose and validate a framework to leverage language-image pretraining representations for training-free zero-shot sketch-to-image synthesis. We show that disentangled content and style representations can be utilized to guide image generators to employ them as sketch-to-image generators without (re-)training any parameters. Our approach for disentangling style and content entails a simple method consisting of elementary arithmetic assuming compositionality of information in representations of input sketches. Our results demonstrate that this approach is competitive with stat…
Consistent Zero-shot 3D Texture Synthesis Using Geometry-aware Diffusion and Temporal Video Models
Department of Image, Chung-Ang University（Chung-Ang大学图像系）；Graphics AI Lab, NCSOFT（NCSOFT图形AI实验室）；Department of Computer Science, University of Seoul（首尔大学计算机科学系）
Institute of Computer Science and Technology, Peking University（北京大学计算机科学技术研究所）
Zero-Shot Learning (ZSL) in video classification is a promising research direction, which aims to tackle the challenge from explosive growth of video categories. Most existing methods exploit seen-to-unseen correlation via learning a projection between visual and semantic spaces. However, such projection-based paradigms cannot fully utilize the discriminative information implied in data distribution, and commonly suffer from the information degradation issue caused by "heterogeneity gap". In this paper, we propose a visual data synthesis framework via GAN to address these problems. Specificall…
Generative Adversarial Networks (GANs) have shown remarkable performance in image synthesis tasks, but typically require a large number of training samples to achieve high-quality synthesis. This paper proposes a simple and effective method, Few-Shot GAN (FSGAN), for adapting GANs in few-shot settings (less than 100 images). FSGAN repurposes component analysis techniques and learns to adapt the singular values of the pre-trained weights while freezing the corresponding singular vectors. This provides a highly expressive parameter space for adaptation while constraining changes to the pretraine…
University of Tsukuba（筑波大学）；Universi（Universi（注：原文中“Univeristy”应为“University”的拼写错误，正确机构为筑波大学））
This paper tackles a challenging problem of generating photorealistic images from semantic layouts in few-shot scenarios where annotated training pairs are hardly available but pixel-wise annotation is quite costly. We present a training strategy that performs pseudo labeling of semantic masks using the StyleGAN prior. Our key idea is to construct a simple mapping between the StyleGAN feature and each semantic class from a few examples of semantic masks. With such mappings, we can generate an unlimited number of pseudo semantic masks from random noise to train an encoder for controlling a pre-…
The Hong Kong University of Science and Technology（香港科技大学）；University of Science and Technology of China（中国科学技术大学）；University of Surrey（萨里大学）；Microsoft（微软公司）；National University of Singapore（新加坡国立大学）；Inner Mongolia University（内蒙古大学）
We propose a neural talking-head video synthesis model and demonstrate its application to video conferencing. Our model learns to synthesize a talking-head video using a source image containing the target person's appearance and a driving video that dictates the motion in the output. Our motion is encoded based on a novel keypoint representation, where the identity-specific and motion-related information is decomposed unsupervisedly. Extensive experimental validation shows that our model outperforms competing methods on benchmark datasets. Moreover, our compact keypoint representation enables …
Requirements of large amounts of data is a difficulty in training many GANs. Data efficient GANs involve fitting a generators continuous target distribution with a limited discrete set of data samples, which is a difficult task. Single image methods have focused on modeling the internal distribution of a single image and generating its samples. While single image methods can synthesize image samples with diversity, they do not model multiple images or capture the inherent relationship possible between two images. Given only a handful of images, we are interested in generating samples and explo…
We introduce a segmentation-guided approach to synthesise images that integrate features from two distinct domains. Images synthesised by our dual-domain model belong to one domain within the semantic mask, and to another in the rest of the image - smoothly integrated. We build on the successes of few-shot StyleGAN and single-shot semantic segmentation to minimise the amount of training required in utilising two domains. The method combines a few-shot cross-domain StyleGAN with a latent optimiser to achieve images containing features of two distinct domains. We use a segmentation-guided percep…
We propose a Text-to-Speech method to create an unseen expressive style using one utterance of expressive speech of around one second. Specifically, we enhance the disentanglement capabilities of a state-of-the-art sequence-to-sequence based system with a Variational AutoEncoder (VAE) and a Householder Flow. The proposed system provides a 22% KL-divergence reduction while jointly improving perceptual metrics over state-of-the-art. At synthesis time we use one example of expressive style as a reference input to the encoder for generating any text in the desired style. Perceptual MUSHRA evaluati…
Wangxuan Institute of Computer Technology, Peking University（北京大学王选计算机研究所）
Automatic generation of artistic glyph images is a challenging task that attracts many research interests. Previous methods either are specifically designed for shape synthesis or focus on texture transfer. In this paper, we propose a novel model, AGIS-Net, to transfer both shape and texture styles in one-stage with only a few stylized samples. To achieve this goal, we first disentangle the representations for content and style by using two encoders, ensuring the multi-content and multi-style generation. Then we utilize two collaboratively working decoders to generate the glyph shape image and…
To detect bias in face recognition networks, it can be useful to probe a network under test using samples in which only specific attributes vary in some controlled way. However, capturing a sufficiently large dataset with specific control over the attributes of interest is difficult. In this work, we describe a simulator that applies specific head pose and facial expression adjustments to images of previously unseen people. The simulator first fits a 3D morphable model to a provided image, applies the desired head pose and facial expression controls, then renders the model into an image. Next,…
University of Amsterdam（阿姆斯特丹大学）；Mohamed Bin Zayed University of Artificial Intelligence（穆罕默德·本·扎耶德人工智能大学）；Inception Institute of Artificial Intelligence（起源人工智能研究院）
Zero-shot learning strives to classify unseen categories for which no data is available during training. In the generalized variant, the test samples can further belong to seen or unseen categories. The state-of-the-art relies on Generative Adversarial Networks that synthesize unseen class features by leveraging class-specific semantic embeddings. During training, they generate semantically consistent features, but discard this constraint during feature synthesis and classification. We propose to enforce semantic consistency at all stages of (generalized) zero-shot learning: training, feature …
DreamShot: Personalized Storyboard Synthesis with Video Diffusion Prior
Sun Yat-sen University（中山大学）；Peng Cheng Laboratory（鹏城实验室）；ByteDance Intelligent Creation（字节跳动智能创作）；Guangdong Key Laboratory of Big Data Analysis and Processing（广东省大数据分析与处理重点实验室）
HFH-Font: Few-shot Chinese Font Synthesis with Higher Quality, Faster Speed, and Higher Resolution
Wangxuan Institute of Computer Technology, Peking University（北京大学王选计算机研究所）；State Key Laboratory of General Artificial Intelligence, Peking University（北京大学通用人工智能国家重点实验室）
Learning light-weight yet expressive deep networks in both image synthesis and image recognition remains a challenging problem. Inspired by a more recent observation that it is the data-specificity that makes the multi-head self-attention (MHSA) in the Transformer model so powerful, this paper proposes to extend the widely adopted light-weight Squeeze-Excitation (SE) module to be spatially-adaptive to reinforce its data specificity, as a convolutional alternative of the MHSA, while retaining the efficiency of SE and the inductive basis of convolution. It presents two designs of spatially-adapt…
Key Laboratory of Multimedia Trusted Perception and Efficient Computing（多媒体可信感知与高效计算重点实验室）；Ministry of Education of China（中华人民共和国教育部）；Xiamen University（厦门大学）；VIVO
One-Shot Novel View and Pose Human Image Synthesis via 3D Prior Guided Diffusion Model
PCA Lab, Key Lab of Intelligent Perception and Systems for High-Dimensional Information of Ministry of Education, and Jiangsu Key Lab of Image and Video Understanding for Social Security, School of Computer Science and Engineering, Nanjing University of Science and Technology（南京理工大学计算机科学与工程学院教育部高维信息智能感知与系统重点实验室、江苏省社会安全图像与视频理解重点实验室及PCA实验室）；Advanced Laser Technology Laboratory of Anhui Province, Electronic Engineering Institute, National University of Defense Technology, and Jianghuai Advance Technology Center（国防科技大学电子工程学院安徽省先进激光技术实验室及江淮前沿技术中心）
One-Shot Learning for Pose-Guided Person Image Synthesis in the Wild
University of Electronic Science and Technology of China（电子科技大学）；China Mobile Zijin (Jiangsu) Innovation Research Institute Co., Ltd（中国移动紫金（江苏）创新研究院有限公司）；Zhejiang Sci-Tech University（浙江理工大学）；Jilin University（吉林大学）；Huawei Canada（华为加拿大公司）；Nanjing University（南京大学）；China Mobile Research Institute（中国移动研究院）
Dream3D: Zero-Shot Text-to-3D Synthesis Using 3D Shape Prior and Text-to-Image Diffusion Models
ARC Lab（ARC实验室）；ShanghaiTech University（上海科技大学）；Tencent PCG（腾讯平台与内容事业群）；Shanghai Engineering Research Center of Intelligent Vision and Imaging（上海智能视觉与成像工程技术研究中心）；Shanghai Engineering Research Center of Energy Efficient and Custom AI IC（上海能效与定制人工智能集成电路工程技术研究中心）
We present DietNeRF, a 3D neural scene representation estimated from a few images. Neural Radiance Fields (NeRF) learn a continuous volumetric representation of a scene through multi-view consistency, and can be rendered from novel viewpoints by ray casting. While NeRF has an impressive ability to reconstruct geometry and fine details given many images, up to 100 for challenging 360° scenes, it often finds a degenerate solution to its image reconstruction objective when only a few input views are available. To improve few-shot quality, we propose DietNeRF. We introduce an auxiliary semantic co…
Renmin University of China（中国人民大学）；Peking University（北京大学）；Queen Mary University of London（伦敦玛丽女王大学）；Samsung AI Centre（三星人工智能中心）
Zero-shot learning (ZSL) is made possible by learning a projection function between a feature space and a semantic space (e.g.,~an attribute space). Key to ZSL is thus to learn a projection that is robust against the often large domain gap between the seen and unseen class domains. In this work, this is achieved by unseen class data synthesis and robust projection function learning. Specifically, a novel semantic data synthesis strategy is proposed, by which semantic class prototypes (e.g., attribute vectors) are used to simply perturb seen class data for generating unseen class ones. As in an…
Visual cognition of primates is superior to that of artificial neural networks in its ability to 'envision' a visual object, even a newly-introduced one, in different attributes including pose, position, color, texture, etc. To aid neural networks to envision objects with different attributes, we propose a family of objective functions, expressed on groups of examples, as a novel learning framework that we term Group-Supervised Learning (GSL). GSL allows us to decompose inputs into a disentangled representation with swappable components, that can be recombined to synthesize new samples. For in…
Nanjing University（南京大学）；University of Southern California（南加州大学）
Object recognition in the real-world requires handling long-tailed or even open-ended data. An ideal visual system needs to recognize the populated head visual concepts reliably and meanwhile efficiently learn about emerging new tail categories with a few training instances. Class-balanced many-shot learning and few-shot learning tackle one side of this problem, by either learning strong classifiers for head or learning to learn few-shot classifiers for the tail. In this paper, we investigate the problem of generalized few-shot learning (GFSL) -- a model during the deployment is required to le…
University of Sheffield（谢菲尔德大学）；University of East Anglia（东英吉利大学）；University of Electronic Science and Technology of China（电子科技大学）；Tsinghua University（清华大学）；Northumbria University（诺森比亚大学）
Robust object recognition systems usually rely on powerful feature extraction mechanisms from a large number of real images. However, in many realistic applications, collecting sufficient images for ever-growing new classes is unattainable. In this paper, we propose a new Zero-shot learning (ZSL) framework that can synthesise visual features for unseen classes without acquiring real images. Using the proposed Unseen Visual Data Synthesis (UVDS) algorithm, semantic attributes are effectively utilised as an intermediate clue to synthesise unseen visual features at the training stage. Hereafter, …
Neural Radiance Fields (NeRF) have led to breakthroughs in the novel view synthesis problem. Positional Encoding (P.E.) is a critical factor that brings the impressive performance of NeRF, where low-dimensional coordinates are mapped to high-dimensional space to better recover scene details. However, blindly increasing the frequency of P.E. leads to overfitting when the reconstruction problem is highly underconstrained, \eg, few-shot images for training. We harness low-frequency neural fields to regularize high-frequency neural fields from overfitting to better address the problem of few-shot …
