Event cameras are bio-inspired cameras which can measure the change of intensity asynchronously with high temporal resolution. One of the event cameras' advantages is that they do not suffer from motion blur when recording high-speed scenes. In this paper, we formulate the deblurring task on traditional cameras directed by events to be a residual learning one, and we propose corresponding network architectures for effective learning of deblurring and high frame rate video generation tasks. We first train a modified U-Net network to restore a sharp image from a blurry image using corresponding events. Then we train another similar network with different downsampling blocks to generate high frame rate video using the restored sharp image and events. Experiment results show that our method can restore sharper images and videos than state-of-the-art methods.
Video prediction is a pixel-wise dense prediction task to infer future frames based on past frames. Missing appearance details and motion blur are still two major problems for current predictive models, which lead to image distortion and temporal inconsistency. In this paper, we point out the necessity of exploring multi-frequency analysis to deal with the two problems. Inspired by the frequency band decomposition characteristic of Human Vision System (HVS), we propose a video prediction network based on multi-level wavelet analysis to deal with spatial and temporal information in a unified manner. Specifically, the multi-level spatial discrete wavelet transform decomposes each video frame into anisotropic sub-bands with multiple frequencies, helping to enrich structural information and reserve fine details. On the other hand, multi-level temporal discrete wavelet transform which operates on time axis decomposes the frame sequence into sub-band groups of different frequencies to accurately capture multi-frequency motions under a fixed frame rate. Extensive experiments on diverse datasets demonstrate that our model shows significant improvements on fidelity and temporal consistency over state-of-the-art works.
Real-world talking faces often accompany with natural head movement. However, most existing talking face video generation methods only consider facial animation with fixed head pose. In this paper, we address this problem by proposing a deep neural network model that takes an audio signal A of a source person and a very short video V of a target person as input, and outputs a synthesized high-quality talking face video with personalized head pose (making use of the visual information in V), expression and lip synchronization (by considering both A and V). The most challenging issue in our work is that natural poses often cause in-plane and out-of-plane head rotations, which makes synthesized talking face video far from realistic. To address this challenge, we reconstruct 3D face animation and re-render it into synthesized frames. To fine tune these frames into realistic ones with smooth background transition, we propose a novel memory-augmented GAN module. By first training a general mapping based on a publicly available dataset and fine-tuning the mapping using the input short video of target person, we develop an effective strategy that only requires a small number of frames (about 300 frames) to learn personalized talking behavior including head pose. Extensive experiments and two user studies show that our method can generate high-quality (i.e., personalized head movements, expressions and good lip synchronization) talking face videos, which are naturally looking with more distinguishing head movement effects than the state-of-the-art methods.
Designing video prediction models that account for the inherent uncertainty of the future is challenging. Most works in the literature are based on stochastic image-autoregressive recurrent networks, which raises several performance and applicability issues. An alternative is to use fully latent temporal models which untie frame synthesis and temporal dynamics. However, no such model for stochastic video prediction has been proposed in the literature yet, due to design and training difficulties. In this paper, we overcome these difficulties by introducing a novel stochastic temporal model whose dynamics are governed in a latent space by a residual update rule. This first-order scheme is motivated by discretization schemes of differential equations. It naturally models video dynamics as it allows our simpler, more interpretable, latent model to outperform prior state-of-the-art methods on challenging datasets.
This work presents an analysis of the discriminators used in Generative Adversarial Networks (GANs) for Video. We show that unconstrained video discriminator architectures induce a loss surface with high curvature which make optimisation difficult. We also show that this curvature becomes more extreme as the maximal kernel dimension of video discriminators increases. With these observations in hand, we propose a family of efficient Lower-Dimensional Video Discriminators for GANs (LDVD GANs). The proposed family of discriminators improve the performance of video GAN models they are applied to and demonstrate good performance on complex and diverse datasets such as UCF-101. In particular, we show that they can double the performance of Temporal-GANs and provide for state-of-the-art performance on a single GPU.
In this work, we propose a modeling technique for jointly training image and video generation models by simultaneously learning to map latent variables with a fixed prior onto real images and interpolate over images to generate videos. The proposed approach models the variations in representations using residual vectors encoding the change at each time step over a summary vector for the entire video. We utilize the technique to jointly train an image generation model with a fixed prior along with a video generation model lacking constraints such as disentanglement. The joint training enables the image generator to exploit temporal information while the video generation model learns to flexibly share information across frames. Moreover, experimental results verify our approach's compatibility with pre-training on videos or images and training on datasets containing a mixture of both. A comprehensive set of quantitative and qualitative evaluations reveal the improvements in sample quality and diversity over both video generation and image generation baselines. We further demonstrate the technique's capabilities of exploiting similarity in features across frames by applying it to a model based on decomposing the video into motion and content. The proposed model allows minor variations in content across frames while maintaining the temporal dependence through latent vectors encoding the pose or motion features.
We present a learning-based approach with pose perceptual loss for automatic music video generation. Our method can produce a realistic dance video that conforms to the beats and rhymes of almost any given music. To achieve this, we firstly generate a human skeleton sequence from music and then apply the learned pose-to-appearance mapping to generate the final video. In the stage of generating skeleton sequences, we utilize two discriminators to capture different aspects of the sequence and propose a novel pose perceptual loss to produce natural dances. Besides, we also provide a new cross-modal evaluation to evaluate the dance quality, which is able to estimate the similarity between two modalities of music and dance. Finally, a user study is conducted to demonstrate that dance video synthesized by the presented approach produces surprisingly realistic results. The results are shown in the supplementary video at https://youtu.be/0rMuFMZa_K4
Image stabilization performed during imaging and/or post-processing poses one of the most significant challenges to photo-response non-uniformity based source camera attribution from videos. When performed digitally, stabilization involves cropping, warping, and inpainting of video frames to eliminate unwanted camera motion. Hence, successful attribution requires the inversion of these transformations in a blind manner. To address this challenge, we introduce a source camera verification method for videos that takes into account the spatially variant nature of stabilization transformations and assumes a larger degree of freedom in their search. Our method identifies transformations at a sub-frame level, incorporates a number of constraints to validate their correctness, and offers computational flexibility in the search for the correct transformation. The method also adopts a holistic approach in countering disruptive effects of other video generation steps, such as video coding and downsizing, for more reliable attribution. Tests performed on one public and two custom datasets show that the proposed method is able to verify the source of 23-30% of all videos that underwent stronger stabilization, depending on computation load, without a significant impact on false attribution.
Creating realistic human videos entails the challenge of being able to simultaneously generate both appearance, as well as motion. To tackle this challenge, we introduce G$^{3}$AN, a novel spatio-temporal generative model, which seeks to capture the distribution of high dimensional video data and to model appearance and motion in disentangled manner. The latter is achieved by decomposing appearance and motion in a three-stream Generator, where the main stream aims to model spatio-temporal consistency, whereas the two auxiliary streams augment the main stream with multi-scale appearance and motion features, respectively. An extensive quantitative and qualitative analysis shows that our model systematically and significantly outperforms state-of-the-art methods on the facial expression datasets MUG and UvA-NEMO, as well as the Weizmann and UCF101 datasets on human action. Additional analysis on the learned latent representations confirms the successful decomposition of appearance and motion. Source code and pre-trained models are publicly available.
Human activity videos involve rich, varied interactions between people and objects. In this paper we develop methods for generating such videos -- making progress toward addressing the important, open problem of video generation in complex scenes. In particular, we introduce the task of generating human-object interaction videos in a zero-shot compositional setting, i.e., generating videos for action-object compositions that are unseen during training, having seen the target action and target object separately. This setting is particularly important for generalization in human activity video generation, obviating the need to observe every possible action-object combination in training and thus avoiding the combinatorial explosion involved in modeling complex scenes. To generate human-object interaction videos, we propose a novel adversarial framework HOI-GAN which includes multiple discriminators focusing on different aspects of a video. To demonstrate the effectiveness of our proposed framework, we perform extensive quantitative and qualitative evaluation on two challenging datasets: EPIC-Kitchens and 20BN-Something-Something v2.
Hand gestures are a natural means of interaction in Augmented Reality and Virtual Reality (AR/VR) applications. Recently, there has been an increased focus on removing the dependence of accurate hand gesture recognition on complex sensor setup found in expensive proprietary devices such as the Microsoft HoloLens, Daqri and Meta Glasses. Most such solutions either rely on multi-modal sensor data or deep neural networks that can benefit greatly from abundance of labelled data. Datasets are an integral part of any deep learning based research. They have been the principal reason for the substantial progress in this field, both, in terms of providing enough data for the training of these models, and, for benchmarking competing algorithms. However, it is becoming increasingly difficult to generate enough labelled data for complex tasks such as hand gesture recognition. The goal of this work is to introduce a framework capable of generating photo-realistic videos that have labelled hand bounding box and fingertip that can help in designing, training, and benchmarking models for hand-gesture recognition in AR/VR applications. We demonstrate the efficacy of our framework in generating videos with diverse backgrounds.
Recent state-of-the-art video generation systems employ Generative Adversarial Networks (GANs) or Variational Autoencoders (VAEs) to produce novel videos. However, VAE models typically produce blurry outputs when faced with sub-optimal conditioning of the input, and GANs are known to be unstable for large output sizes. In addition, the output videos of these models are difficult to evaluate, partly because the GAN loss function is not an accurate measure of convergence. In this work, we propose using a state-of-the-art neural flow generator called Glow to generate videos conditioned on a textual label, one frame at a time. Neural flow models are more stable than standard GANs, as they only optimize a single cross entropy loss function, which is monotonic and avoids the circular convergence issues of the GAN minimax objective. In addition, we also show how to condition Glow on external context, while still preserving the invertible nature of each "flow" layer. Finally, we evaluate the proposed Glow model by calculating cross entropy on a held-out validation set of videos, in order to compare multiple versions of the proposed model via an ablation study. We show generated videos and discuss future improvements.
Generation of realistic high-resolution videos of human subjects is a challenging and important task in computer vision. In this paper, we focus on human motion transfer - generation of a video depicting a particular subject, observed in a single image, performing a series of motions exemplified by an auxiliary (driving) video. Our GAN-based architecture, DwNet, leverages dense intermediate pose-guided representation and refinement process to warp the required subject appearance, in the form of the texture, from a source image into a desired pose. Temporal consistency is maintained by further conditioning the decoding process within a GAN on the previously generated frame. In this way a video is generated in an iterative and recurrent fashion. We illustrate the efficacy of our approach by showing state-of-the-art quantitative and qualitative performance on two benchmark datasets: TaiChi and Fashion Modeling. The latter is collected by us and will be made publicly available to the community.
Deep video action recognition models have been highly successful in recent years but require large quantities of manually annotated data, which are expensive and laborious to obtain. In this work, we investigate the generation of synthetic training data for video action recognition, as synthetic data have been successfully used to supervise models for a variety of other computer vision tasks. We propose an interpretable parametric generative model of human action videos that relies on procedural generation, physics models and other components of modern game engines. With this model we generate a diverse, realistic, and physically plausible dataset of human action videos, called PHAV for "Procedural Human Action Videos". PHAV contains a total of 39,982 videos, with more than 1,000 examples for each of 35 action categories. Our video generation approach is not limited to existing motion capture sequences: 14 of these 35 categories are procedurally defined synthetic actions. In addition, each video is represented with 6 different data modalities, including RGB, optical flow and pixel-level semantic labels. These modalities are generated almost simultaneously using the Multiple Render Targets feature of modern GPUs. In order to leverage PHAV, we introduce a deep multi-task (i.e. that considers action classes from multiple datasets) representation learning architecture that is able to simultaneously learn from synthetic and real video datasets, even when their action categories differ. Our experiments on the UCF-101 and HMDB-51 benchmarks suggest that combining our large set of synthetic videos with small real-world datasets can boost recognition performance. Our approach also significantly outperforms video representations produced by fine-tuning state-of-the-art unsupervised generative models of videos.
We identify two pathological cases of temporal inconsistencies in video generation: video freezing and video looping. To better quantify the temporal diversity, we propose a class of complementary metrics that are effective, easy to implement, data agnostic, and interpretable. Further, we observe that current state-of-the-art models are trained on video samples of fixed length thereby inhibiting long-term modeling. To address this, we reformulate the problem of video generation as a Markov Decision Process (MDP). The underlying idea is to represent motion as a stochastic process with an infinite forecast horizon to overcome the fixed length limitation and to mitigate the presence of temporal artifacts. We show that our formulation is easy to integrate into the state-of-the-art MoCoGAN framework. Our experiments on the Human Actions and UCF-101 datasets demonstrate that our MDP-based model is more memory efficient and improves the video quality both in terms of the new and established metrics.
Video contents have become a critical tool for promoting products in E-commerce. However, the lack of automatic promotional video generation solutions makes large-scale video-based promotion campaigns infeasible. The first step of automatically producing promotional videos is to generate visual storylines, which is to select the building block footage and place them in an appropriate order. This task is related to the subjective viewing experience. It is hitherto performed by human experts and thus, hard to scale. To address this problem, we propose WundtBackpack, an algorithmic approach to generate storylines based on available visual materials, which can be video clips or images. It consists of two main parts, 1) the Learnable Wundt Curve to evaluate the perceived persuasiveness based on the stimulus intensity of a sequence of visual materials, which only requires a small volume of data to train; and 2) a clustering-based backpacking algorithm to generate persuasive sequences of visual materials while considering video length constraints. In this way, the proposed approach provides a dynamic structure to empower artificial intelligence (AI) to organize video footage in order to construct a sequence of visual stimuli with persuasive power. Extensive real-world experiments show that our approach achieves close to 10% higher perceived persuasiveness scores by human testers, and 12.5% higher expected revenue compared to the best performing state-of-the-art approach.
Existing person video generation methods either lack the flexibility in controlling both the appearance and motion, or fail to preserve detailed appearance and temporal consistency. In this paper, we tackle the problem of motion transfer for generating person videos, which provides controls on both the appearance and the motion. Specifically, we transfer the motion of one person in a target video to another person in a source video, while preserving the appearance of the source person. Besides only relying on one source frame as the existing state-of-the-art methods, our proposed method integrates information from multiple source frames based on a spatio-temporal attention mechanism to preserve rich appearance details. In addition to a spatial discriminator employed for encouraging the frame-level fidelity, a multi-range temporal discriminator is adopted to enforce the generated video to resemble temporal dynamics of a real video in various time ranges. A challenging real-world dataset, which contains about 500 dancing video clips with complex and unpredictable motions, is collected for the training and testing. Extensive experiments show that the proposed method can produce more photo-realistic and temporally consistent person videos than previous methods. As our method decomposes the syntheses of the foreground and background into two branches, a flexible background substitution application can also be achieved.
Predicting future frames in natural video sequences is a new challenge that is receiving increasing attention in the computer vision community. However, existing models suffer from severe loss of temporal information when the predicted sequence is long. Compared to previous methods focusing on generating more realistic contents, this paper extensively studies the importance of sequential order information for video generation. A novel Shuffling sEquence gEneration network (SEE-Net) is proposed that can learn to discriminate unnatural sequential orders by shuffling the video frames and comparing them to the real video sequence. Systematic experiments on three datasets with both synthetic and real-world videos manifest the effectiveness of shuffling sequence generation for video prediction in our proposed model and demonstrate state-of-the-art performance by both qualitative and quantitative evaluations. The source code is available at https://github.com/andrewjywang/SEENet.
Generative models of natural images have progressed towards high fidelity samples by the strong leveraging of scale. We attempt to carry this success to the field of video modeling by showing that large Generative Adversarial Networks trained on the complex Kinetics-600 dataset are able to produce video samples of substantially higher complexity and fidelity than previous work. Our proposed model, Dual Video Discriminator GAN (DVD-GAN), scales to longer and higher resolution videos by leveraging a computationally efficient decomposition of its discriminator. We evaluate on the related tasks of video synthesis and video prediction, and achieve new state-of-the-art Fr\'echet Inception Distance for prediction for Kinetics-600, as well as state-of-the-art Inception Score for synthesis on the UCF-101 dataset, alongside establishing a strong baseline for synthesis on Kinetics-600.
Due to the statistical complexity of video, the high degree of inherent stochasticity, and the sheer amount of data, generating natural video remains a challenging task. State-of-the-art video generation models often attempt to address these issues by combining sometimes complex, usually video-specific neural network architectures, latent variable models, adversarial training and a range of other methods. Despite their often high complexity, these approaches still fall short of generating high quality video continuations outside of narrow domains and often struggle with fidelity. In contrast, we show that conceptually simple autoregressive video generation models based on a three-dimensional self-attention mechanism achieve competitive results across multiple metrics on popular benchmark datasets, for which they produce continuations of high fidelity and realism. We also present results from training our models on Kinetics, a large scale action recognition dataset comprised of YouTube videos exhibiting phenomena such as camera movement, complex object interactions and diverse human movement. While modeling these phenomena consistently remains elusive, we hope that our results, which include occasional realistic continuations encourage further research on comparatively complex, large scale datasets such as Kinetics.