This paper presents a unified multimodal pre-trained model called N\"UWA that can generate new or manipulate existing visual data (i.e., images and videos) for various visual synthesis tasks. To cover language, image, and video at the same time for different scenarios, a 3D transformer encoder-decoder framework is designed, which can not only deal with videos as 3D data but also adapt to texts and images as 1D and 2D data, respectively. A 3D Nearby Attention (3DNA) mechanism is also proposed to consider the nature of the visual data and reduce the computational complexity. We evaluate N\"UWA on 8 downstream tasks. Compared to several strong baselines, N\"UWA achieves state-of-the-art results on text-to-image generation, text-to-video generation, video prediction, etc. Furthermore, it also shows surprisingly good zero-shot capabilities on text-guided image and video manipulation tasks. Project repo is https://github.com/microsoft/NUWA.
Video generation is an interesting problem in computer vision. It is quite popular for data augmentation, special effect in move, AR/VR and so on. With the advances of deep learning, many deep generative models have been proposed to solve this task. These deep generative models provide away to utilize all the unlabeled images and videos online, since it can learn deep feature representations with unsupervised manner. These models can also generate different kinds of images, which have great value for visual application. However generating a video would be much more challenging since we need to model not only the appearances of objects in the video but also their temporal motion. In this work, we will break down any frame in the video into content and pose. We first extract the pose information from a video using a pre-trained human pose detection and use a generative model to synthesize the video based on the content code and pose code.
Video Generation is a relatively new and yet popular subject in machine learning due to its vast variety of potential applications and its numerous challenges. Current methods in Video Generation provide the user with little or no control over the exact specification of how the objects in the generate video are to be moved and located at each frame, that is, the user can't explicitly control how each object in the video should move. In this paper we propose a novel method that allows the user to move any number of objects of a single initial frame just by drawing bounding boxes over those objects and then moving those boxes in the desired path. Our model utilizes two Autoencoders to fully decompose the motion and content information in a video and achieves results comparable to well-known baseline and state of the art methods.
Training computer-vision related algorithms on medical images for disease diagnosis or image segmentation is difficult due to the lack of training data, labeled samples, and privacy concerns. For this reason, a robust generative method to create synthetic data is highly sought after. However, most three-dimensional image generators require additional image input or are extremely memory intensive. To address these issues we propose adapting video generation techniques for 3-D image generation. Using the temporal GAN (TGAN) architecture, we show we are able to generate realistic head and neck PET images. We also show that by conditioning the generator on tumour masks, we are able to control the geometry and location of the tumour in the generated images. To test the utility of the synthetic images, we train a segmentation model using the synthetic images. Synthetic images conditioned on real tumour masks are automatically segmented, and the corresponding real images are also segmented. We evaluate the segmentations using the Dice score and find the segmentation algorithm performs similarly on both datasets (0.65 synthetic data, 0.70 real data). Various radionomic features are then calculated over the segmented tumour volumes for each data set. A comparison of the real and synthetic feature distributions show that seven of eight feature distributions had statistically insignificant differences (p>0.05). Correlation coefficients were also calculated between all radionomic features and it is shown that all of the strong statistical correlations in the real data set are preserved in the synthetic data set.
Transferring human motion from a source to a target person poses great potential in computer vision and graphics applications. A crucial step is to manipulate sequential future motion while retaining the appearance characteristic.Previous work has either relied on crafted 3D human models or trained a separate model specifically for each target person, which is not scalable in practice.This work studies a more general setting, in which we aim to learn a single model to parsimoniously transfer motion from a source video to any target person given only one image of the person, named as Collaborative Parsing-Flow Network (CPF-Net). The paucity of information regarding the target person makes the task particularly challenging to faithfully preserve the appearance in varying designated poses. To address this issue, CPF-Net integrates the structured human parsing and appearance flow to guide the realistic foreground synthesis which is merged into the background by a spatio-temporal fusion module. In particular, CPF-Net decouples the problem into stages of human parsing sequence generation, foreground sequence generation and final video generation. The human parsing generation stage captures both the pose and the body structure of the target. The appearance flow is beneficial to keep details in synthesized frames. The integration of human parsing and appearance flow effectively guides the generation of video frames with realistic appearance. Finally, the dedicated designed fusion network ensure the temporal coherence. We further collect a large set of human dancing videos to push forward this research field. Both quantitative and qualitative results show our method substantially improves over previous approaches and is able to generate appealing and photo-realistic target videos given any input person image. All source code and dataset will be released at https://github.com/xiezhy6/CPF-Net.
We demonstrate ViDA-MAN, a digital-human agent for multi-modal interaction, which offers realtime audio-visual responses to instant speech inquiries. Compared to traditional text or voice-based system, ViDA-MAN offers human-like interactions (e.g, vivid voice, natural facial expression and body gestures). Given a speech request, the demonstration is able to response with high quality videos in sub-second latency. To deliver immersive user experience, ViDA-MAN seamlessly integrates multi-modal techniques including Acoustic Speech Recognition (ASR), multi-turn dialog, Text To Speech (TTS), talking heads video generation. Backed with large knowledge base, ViDA-MAN is able to chat with users on a number of topics including chit-chat, weather, device control, News recommendations, booking hotels, as well as answering questions via structured knowledge.
Clothes style transfer for person video generation is a challenging task, due to drastic variations of intra-person appearance and video scenarios. To tackle this problem, most recent AdaIN-based architectures are proposed to extract clothes and scenario features for generation. However, these approaches suffer from being short of fine-grained details and are prone to distort the origin person. To further improve the generation performance, we propose a novel framework with disentangled multi-branch encoders and a shared decoder. Moreover, to pursue the strong video spatio-temporal consistency, an inner-frame discriminator is delicately designed with input being cross-frame difference. Besides, the proposed framework possesses the property of scenario adaptation. Extensive experiments on the TEDXPeople benchmark demonstrate the superiority of our method over state-of-the-art approaches in terms of image quality and video coherence.
Synthesising the spatial and temporal dynamics of the human body skeleton remains a challenging task, not only in terms of the quality of the generated shapes, but also of their diversity, particularly to synthesise realistic body movements of a specific action (action conditioning). In this paper, we propose Kinetic-GAN, a novel architecture that leverages the benefits of Generative Adversarial Networks and Graph Convolutional Networks to synthesise the kinetics of the human body. The proposed adversarial architecture can condition up to 120 different actions over local and global body movements while improving sample quality and diversity through latent space disentanglement and stochastic variations. Our experiments were carried out in three well-known datasets, where Kinetic-GAN notably surpasses the state-of-the-art methods in terms of distribution quality metrics while having the ability to synthesise more than one order of magnitude regarding the number of different actions. Our code and models are publicly available at https://github.com/DegardinBruno/Kinetic-GAN.
This paper proposes a video editor based on OpenShot with several state-of-the-art facial video editing algorithms as added functionalities. Our editor provides an easy-to-use interface to apply modern lip-syncing algorithms interactively. Apart from lip-syncing, the editor also uses audio and facial re-enactment to generate expressive talking faces. The manual control improves the overall experience of video editing without missing out on the benefits of modern synthetic video generation algorithms. This control enables us to lip-sync complex dubbed movie scenes, interviews, television shows, and other visual content. Furthermore, our editor provides features that automatically translate lectures from spoken content, lip-sync of the professor, and background content like slides. While doing so, we also tackle the critical aspect of synchronizing background content with the translated speech. We qualitatively evaluate the usefulness of the proposed editor by conducting human evaluations. Our evaluations show a clear improvement in the efficiency of using human editors and an improved video generation quality. We attach demo videos with the supplementary material clearly explaining the tool and also showcasing multiple results.
Predicting the future frames of a video is a challenging task, in part due to the underlying stochastic real-world phenomena. Prior approaches to solve this task typically estimate a latent prior characterizing this stochasticity, however do not account for the predictive uncertainty of the (deep learning) model. Such approaches often derive the training signal from the mean-squared error (MSE) between the generated frame and the ground truth, which can lead to sub-optimal training, especially when the predictive uncertainty is high. Towards this end, we introduce Neural Uncertainty Quantifier (NUQ) - a stochastic quantification of the model's predictive uncertainty, and use it to weigh the MSE loss. We propose a hierarchical, variational framework to derive NUQ in a principled manner using a deep, Bayesian graphical model. Our experiments on four benchmark stochastic video prediction datasets show that our proposed framework trains more effectively compared to the state-of-the-art models (especially when the training sets are small), while demonstrating better video generation quality and diversity against several evaluation metrics.
A video autoencoder is proposed for learning disentan- gled representations of 3D structure and camera pose from videos in a self-supervised manner. Relying on temporal continuity in videos, our work assumes that the 3D scene structure in nearby video frames remains static. Given a sequence of video frames as input, the video autoencoder extracts a disentangled representation of the scene includ- ing: (i) a temporally-consistent deep voxel feature to represent the 3D structure and (ii) a 3D trajectory of camera pose for each frame. These two representations will then be re-entangled for rendering the input video frames. This video autoencoder can be trained directly using a pixel reconstruction loss, without any ground truth 3D or camera pose annotations. The disentangled representation can be applied to a range of tasks, including novel view synthesis, camera pose estimation, and video generation by motion following. We evaluate our method on several large- scale natural video datasets, and show generalization results on out-of-domain images.
We look into Generative Adversarial Network (GAN), its prevalent variants and applications in a number of sectors. GANs combine two neural networks that compete against one another using zero-sum game theory, allowing them to create much crisper and discrete outputs. GANs can be used to perform image processing, video generation and prediction, among other computer vision applications. GANs can also be utilised for a variety of science-related activities, including protein engineering, astronomical data processing, remote sensing image dehazing, and crystal structure synthesis. Other notable fields where GANs have made gains include finance, marketing, fashion design, sports, and music. Therefore in this article we provide a comprehensive overview of the applications of GANs in a wide variety of disciplines. We first cover the theory supporting GAN, GAN variants, and the metrics to evaluate GANs. Then we present how GAN and its variants can be applied in twelve domains, ranging from STEM fields, such as astronomy and biology, to business fields, such as marketing and finance, and to arts, such as music. As a result, researchers from other fields may grasp how GANs work and apply them to their own study. To the best of our knowledge, this article provides the most comprehensive survey of GAN's applications in different fields.
GANs are able to perform generation and manipulation tasks, trained on a single video. However, these single video GANs require unreasonable amount of time to train on a single video, rendering them almost impractical. In this paper we question the necessity of a GAN for generation from a single video, and introduce a non-parametric baseline for a variety of generation and manipulation tasks. We revive classical space-time patches-nearest-neighbors approaches and adapt them to a scalable unconditional generative model, without any learning. This simple baseline surprisingly outperforms single-video GANs in visual quality and realism (confirmed by quantitative and qualitative evaluations), and is disproportionately faster (runtime reduced from several days to seconds). Other than diverse video generation, we demonstrate other applications using the same framework, including video analogies and spatio-temporal retargeting. Our proposed approach is easily scaled to Full-HD videos. These observations show that the classical approaches, if adapted correctly, significantly outperform heavy deep learning machinery for these tasks. This sets a new baseline for single-video generation and manipulation tasks, and no less important -- makes diverse generation from a single video practically possible for the first time.
We propose a conditional generative adversarial network (GAN) model for zero-shot video generation. In this study, we have explored zero-shot conditional generation setting. In other words, we generate unseen videos from training samples with missing classes. The task is an extension of conditional data generation. The key idea is to learn disentangled representations in the latent space of a GAN. To realize this objective, we base our model on the motion and content decomposed GAN and conditional GAN for image generation. We build the model to find better-disentangled representations and to generate good-quality videos. We demonstrate the effectiveness of our proposed model through experiments on the Weizmann action database and the MUG facial expression database.
Despite having been studied to a great extent, the task of conditional generation of sequences of frames, or videos, remains extremely challenging. It is a common belief that a key step towards solving this task resides in modelling accurately both spatial and temporal information in video signals. A promising direction to do so has been to learn latent variable models that predict the future in latent space and project back to pixels, as suggested in recent literature. Following this line of work and building on top of a family of models introduced in prior work, Neural ODE, we investigate an approach that models time-continuous dynamics over a continuous latent space with a differential equation with respect to time. The intuition behind this approach is that these trajectories in latent space could then be extrapolated to generate video frames beyond the time steps for which the model is trained. We show that our approach yields promising results in the task of future frame prediction on the Moving MNIST dataset with 1 and 2 digits.
This paper introduces Click to Move (C2M), a novel framework for video generation where the user can control the motion of the synthesized video through mouse clicks specifying simple object trajectories of the key objects in the scene. Our model receives as input an initial frame, its corresponding segmentation map and the sparse motion vectors encoding the input provided by the user. It outputs a plausible video sequence starting from the given frame and with a motion that is consistent with user input. Notably, our proposed deep architecture incorporates a Graph Convolution Network (GCN) modelling the movements of all the objects in the scene in a holistic manner and effectively combining the sparse user motion information and image features. Experimental results show that C2M outperforms existing methods on two publicly available datasets, thus demonstrating the effectiveness of our GCN framework at modelling object interactions. The source code is publicly available at https://github.com/PierfrancescoArdino/C2M.
Generating ``bullet-time'' effects of human free-viewpoint videos is critical for immersive visual effects and VR/AR experience. Recent neural advances still lack the controllable and interactive bullet-time design ability for human free-viewpoint rendering, especially under the real-time, dynamic and general setting for our trajectory-aware task. To fill this gap, in this paper we propose a neural interactive bullet-time generator (iButter) for photo-realistic human free-viewpoint rendering from dense RGB streams, which enables flexible and interactive design for human bullet-time visual effects. Our iButter approach consists of a real-time preview and design stage as well as a trajectory-aware refinement stage. During preview, we propose an interactive bullet-time design approach by extending the NeRF rendering to a real-time and dynamic setting and getting rid of the tedious per-scene training. To this end, our bullet-time design stage utilizes a hybrid training set, light-weight network design and an efficient silhouette-based sampling strategy. During refinement, we introduce an efficient trajectory-aware scheme within 20 minutes, which jointly encodes the spatial, temporal consistency and semantic cues along the designed trajectory, achieving photo-realistic bullet-time viewing experience of human activities. Extensive experiments demonstrate the effectiveness of our approach for convenient interactive bullet-time design and photo-realistic human free-viewpoint video generation.
In this demo, we present VirtualConductor, a system that can generate conducting video from any given music and a single user's image. First, a large-scale conductor motion dataset is collected and constructed. Then, we propose Audio Motion Correspondence Network (AMCNet) and adversarial-perceptual learning to learn the cross-modal relationship and generate diverse, plausible, music-synchronized motion. Finally, we combine 3D animation rendering and a pose transfer model to synthesize conducting video from a single given user's image. Therefore, any user can become a virtual conductor through the system.
Random reconstruction of three-dimensional (3D) digital rocks from two-dimensional (2D) slices is crucial for elucidating the microstructure of rocks and its effects on pore-scale flow in terms of numerical modeling, since massive samples are usually required to handle intrinsic uncertainties. Despite remarkable advances achieved by traditional process-based methods, statistical approaches and recently famous deep learning-based models, few works have focused on producing several kinds of rocks with one trained model and allowing the reconstructed samples to satisfy certain given properties, such as porosity. To fill this gap, we propose a new framework, named RockGPT, which is composed of VQ-VAE and conditional GPT, to synthesize 3D samples based on a single 2D slice from the perspective of video generation. The VQ-VAE is utilized to compress high-dimensional input video, i.e., the sequence of continuous rock slices, to discrete latent codes and reconstruct them. In order to obtain diverse reconstructions, the discrete latent codes are modeled using conditional GPT in an autoregressive manner, while incorporating conditional information from a given slice, rock type, and porosity. We conduct two experiments on five kinds of rocks, and the results demonstrate that RockGPT can produce different kinds of rocks with the same model, and the reconstructed samples can successfully meet certain specified porosities. In a broader sense, through leveraging the proposed conditioning scheme, RockGPT constitutes an effective way to build a general model to produce multiple kinds of rocks simultaneously that also satisfy user-defined properties.
Motion is an important cue for video prediction and often utilized by separating video content into static and dynamic components. Most of the previous work utilizing motion is deterministic but there are stochastic methods that can model the inherent uncertainty of the future. Existing stochastic models either do not reason about motion explicitly or make limiting assumptions about the static part. In this paper, we reason about appearance and motion in the video stochastically by predicting the future based on the motion history. Explicit reasoning about motion without history already reaches the performance of current stochastic models. The motion history further improves the results by allowing to predict consistent dynamics several frames into the future. Our model performs comparably to the state-of-the-art models on the generic video prediction datasets, however, significantly outperforms them on two challenging real-world autonomous driving datasets with complex motion and dynamic background.