PyTorchKR Papers

최신 논문

총 358편
태그·기간 등 상세 필터

카테고리 탐색

로그인 후 이 태그 구독

논문 ID: document/8594264

VarNet: Exploring Variations for Unsupervised Video Prediction

Unsupervised video prediction is a very challenging task due to the complexity and diversity in natural scenes. Prior works directly predicting pixels or optical flows either have the blurring problem or require additional assumptions. We highlight that the crux for video frame prediction lies in precisely capturing the inter-frame variations which encompass the movement of objects and the evolution of the surrounding environment. We then present an unsupervised video prediction framework - Variation Network (VarNet) to directly predict the variations between adjacent frames which are then fused with current frame to generate the future frame. In addition, we propose an adaptively re-weighting mechanism for loss function to offer each pixel a fair weight according to the amplitude of its variation. Extensive experiments for both short-term and long-term video prediction are implemented on two advanced datasets - KTH and KITTI with two evaluating metrics - PSNR and SSIM. For the KTH dataset, the VarNet outperforms the state-of-the-art works up to 11.9% on PSNR and 9.5% on SSIM. As for the KITTI dataset, the performance boosts are up to 55.1% on PSNR and 15.9% on SSIM. Moreover, we verify that the generalization ability of our model excels other state-of-the-art methods by testing on the unseen CalTech Pedestrian dataset after being trained on the KITTI dataset. Source code and video are available at https://github.com/jinbeibei/VarNet.

arXiv:2203.10528

Stochastic Video Prediction with Structure and Motion

While stochastic video prediction models enable future prediction under uncertainty, they mostly fail to model the complex dynamics of real-world scenes. For example, they cannot provide reliable predictions for scenes with a moving camera and independently moving foreground objects in driving scenarios. The existing methods fail to fully capture the dynamics of the structured world by only focusing on changes in pixels. In this paper, we assume that there is an underlying process creating observations in a video and propose to factorize it into static and dynamic components. We model the static part based on the scene structure and the ego-motion of the vehicle, and the dynamic part based on the remaining motion of the dynamic objects. By learning separate distributions of changes in foreground and background, we can decompose the scene into static and dynamic parts and separately model the change in each. Our experiments demonstrate that disentangling structure and motion helps stochastic video prediction, leading to better future predictions in complex driving scenarios on two real-world driving datasets, KITTI and Cityscapes.

arXiv:2203.09303공식 코드 · Papers with Code

MSPred: Video Prediction at Multiple Spatio-Temporal Scales with Hierarchical Recurrent Networks

Autonomous systems not only need to understand their current environment, but should also be able to predict future actions conditioned on past states, for instance based on captured camera frames. However, existing models mainly focus on forecasting future video frames for short time-horizons, hence being of limited use for long-term action planning. We propose Multi-Scale Hierarchical Prediction (MSPred), a novel video prediction model able to simultaneously forecast future possible outcomes of different levels of granularity at different spatio-temporal scales. By combining spatial and temporal downsampling, MSPred efficiently predicts abstract representations such as human poses or locations over long time horizons, while still maintaining a competitive performance for video frame prediction. In our experiments, we demonstrate that MSPred accurately predicts future video frames as well as high-level representations (e.g. keypoints or semantics) on bin-picking and action recognition datasets, while consistently outperforming popular approaches for future frame prediction. Furthermore, we ablate different modules and design choices in MSPred, experimentally validating that combining features of different spatial and temporal granularity leads to a superior performance. Code and models to reproduce our experiments can be found in https://github.com/AIS-Bonn/MSPred.

arXiv:2202.00368

Filtered-CoPhy: Unsupervised Learning of Counterfactual Physics in Pixel Space

Learning causal relationships in high-dimensional data (images, videos) is a hard task, as they are often defined on low dimensional manifolds and must be extracted from complex signals dominated by appearance, lighting, textures and also spurious correlations in the data. We present a method for learning counterfactual reasoning of physical processes in pixel space, which requires the prediction of the impact of interventions on initial conditions. Going beyond the identification of structural relationships, we deal with the challenging problem of forecasting raw video over long horizons. Our method does not require the knowledge or supervision of any ground truth positions or other object or scene properties. Our model learns and acts on a suitable hybrid latent representation based on a combination of dense features, sets of 2D keypoints and an additional latent vector per keypoint. We show that this better captures the dynamics of physical processes than purely dense or sparse representations. We introduce a new challenging and carefully designed counterfactual benchmark for predictions in pixel space and outperform strong baselines in physics-inspired ML and video prediction.

arXiv:2201.09152

Generative Adversarial Network Applications in Creating a Meta-Universe

Generative Adversarial Networks (GANs) are machine learning methods that are used in many important and novel applications. For example, in imaging science, GANs are effectively utilized in generating image datasets, photographs of human faces, image and video captioning, image-to-image translation, text-to-image translation, video prediction, and 3D object generation to name a few. In this paper, we discuss how GANs can be used to create an artificial world. More specifically, we discuss how GANs help to describe an image utilizing image/video captioning methods and how to translate the image to a new image using image-to-image translation frameworks in a theme we desire. We articulate how GANs impact creating a customized world.

arXiv:2112.11729

Generalized Local Optimality for Video Steganalysis in Motion Vector Domain

The local optimality of motion vectors (MVs) is an intrinsic property in video coding, and any modifications to the MVs will inevitably destroy this optimality, making it a sensitive indicator of steganography in the MV domain. Thus the local optimality is commonly used to design steganalytic features, and the estimation for local optimality has become a top priority in video steganalysis. However, the local optimality in existing works is often estimated inaccurately or using an unreasonable assumption, limiting its capability in steganalysis. In this paper, we propose to estimate the local optimality in a more reasonable and comprehensive fashion, and generalize the concept of local optimality in two aspects. First, the local optimality measured in a rate-distortion sense is jointly determined by MV and predicted motion vector (PMV), and the variability of PMV will affect the estimation for local optimality. Hence we generalize the local optimality from a static estimation to a dynamic one. Second, the PMV is a special case of MV, and can also reflect the embedding traces in MVs. So we generalize the local optimality from the MV domain to the PMV domain. Based on the two generalizations of local optimality, we construct new types of steganalytic features and also propose feature symmetrization rules to reduce feature dimension. Extensive experiments performed on three databases demonstrate the effectiveness of the proposed features, which achieve state-of-the-art in both accuracy and robustness in various conditions, including cover source mismatch, video prediction methods, video codecs, and video resolutions.

arXiv:2111.12301

Two-stage Rule-induction Visual Reasoning on RPMs with an Application to Video Prediction

Raven's Progressive Matrices (RPMs) are frequently used in evaluating human's visual reasoning ability. Researchers have made considerable efforts in developing systems to automatically solve the RPM problem, often through a black-box end-to-end convolutional neural network for both visual recognition and logical reasoning tasks. Based on the two intrinsic natures of RPM problem, visual recognition and logical reasoning, we propose a Two-stage Rule-Induction Visual Reasoner (TRIVR), which consists of a perception module and a reasoning module, to tackle the challenges of real-world visual recognition and subsequent logical reasoning tasks, respectively. For the reasoning module, we further propose a "2+1" formulation that models human's thinking in solving RPMs and significantly reduces the model complexity. It derives a reasoning rule from each RPM sample, which is not feasible for existing methods. As a result, the proposed reasoning module is capable of yielding a set of reasoning rules modeling human in solving the RPM problems. To validate the proposed method on real-world applications, an RPM-like Video Prediction (RVP) dataset is constructed, where visual reasoning is conducted on RPMs constructed using real-world video frames. Experimental results on various RPM-like datasets demonstrate that the proposed TRIVR achieves a significant and consistent performance gain compared with the state-of-the-art models.

arXiv:2111.12417

NÜWA: Visual Synthesis Pre-training for Neural visUal World creAtion

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.

arXiv:2110.11586

Wide and Narrow: Video Prediction from Context and Motion

Video prediction, forecasting the future frames from a sequence of input frames, is a challenging task since the view changes are influenced by various factors, such as the global context surrounding the scene and local motion dynamics. In this paper, we propose a new framework to integrate these complementary attributes to predict complex pixel dynamics through deep networks. We present global context propagation networks that iteratively aggregate the non-local neighboring representations to preserve the contextual information over the past frames. To capture the local motion pattern of objects, we also devise local filter memory networks that generate adaptive filter kernels by storing the prototypical motion of moving objects in the memory. The proposed framework, utilizing the outputs from both networks, can address blurry predictions and color distortion. We conduct experiments on Caltech pedestrian and UCF101 datasets, and demonstrate state-of-the-art results. Especially for multi-step prediction, we obtain an outstanding performance in quantitative and qualitative evaluation.

arXiv:2110.05881

Fourier-based Video Prediction through Relational Object Motion

The ability to predict future outcomes conditioned on observed video frames is crucial for intelligent decision-making in autonomous systems. Recently, deep recurrent architectures have been applied to the task of video prediction. However, this often results in blurry predictions and requires tedious training on large datasets. Here, we explore a different approach by (1) using frequency-domain approaches for video prediction and (2) explicitly inferring object-motion relationships in the observed scene. The resulting predictions are consistent with the observed dynamics in a scene and do not suffer from blur.

arXiv:2110.03446

A Hierarchical Variational Neural Uncertainty Model for Stochastic Video Prediction

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.

arXiv:2110.02829공식 코드 · Papers with Code

Semantic Prediction: Which One Should Come First, Recognition or Prediction?

The ultimate goal of video prediction is not forecasting future pixel-values given some previous frames. Rather, the end goal of video prediction is to discover valuable internal representations from the vast amount of available unlabeled video data in a self-supervised fashion for downstream tasks. One of the primary downstream tasks is interpreting the scene's semantic composition and using it for decision-making. For example, by predicting human movements, an observer can anticipate human activities and collaborate in a shared workspace. There are two main ways to achieve the same outcome, given a pre-trained video prediction and pre-trained semantic extraction model; one can first apply predictions and then extract semantics or first extract semantics and then predict. We investigate these configurations using the Local Frequency Domain Transformer Network (LFDTN) as the video prediction model and U-Net as the semantic extraction model on synthetic and real datasets.

arXiv:2109.06474

Space Time Recurrent Memory Network

Transformers have recently been popular for learning and inference in the spatial-temporal domain. However, their performance relies on storing and applying attention to the feature tensor of each frame in video. Hence, their space and time complexity increase linearly as the length of video grows, which could be very costly for long videos. We propose a novel visual memory network architecture for the learning and inference problem in the spatial-temporal domain. We maintain a fixed set of memory slots in our memory network and propose an algorithm based on Gumbel-Softmax to learn an adaptive strategy to update this memory. Finally, this architecture is benchmarked on the video object segmentation (VOS) and video prediction problems. We demonstrate that our memory architecture achieves state-of-the-art results, outperforming transformer-based methods on VOS and other recent methods on video prediction while maintaining constant memory capacity independent of the sequence length.

arXiv:2109.02137

Efficient Action Recognition Using Confidence Distillation

Modern neural networks are powerful predictive models. However, when it comes to recognizing that they may be wrong about their predictions, they perform poorly. For example, for one of the most common activation functions, the ReLU and its variants, even a well-calibrated model can produce incorrect but high confidence predictions. In the related task of action recognition, most current classification methods are based on clip-level classifiers that densely sample a given video for non-overlapping, same-sized clips and aggregate the results using an aggregation function - typically averaging - to achieve video level predictions. While this approach has shown to be effective, it is sub-optimal in recognition accuracy and has a high computational overhead. To mitigate both these issues, we propose the confidence distillation framework to teach a representation of uncertainty of the teacher to the student sampler and divide the task of full video prediction between the student and the teacher models. We conduct extensive experiments on three action recognition datasets and demonstrate that our framework achieves significant improvements in action recognition accuracy (up to 20%) and computational efficiency (more than 40%).

arXiv:2108.05658

Conditional Temporal Variational AutoEncoder for Action Video Prediction

To synthesize a realistic action sequence based on a single human image, it is crucial to model both motion patterns and diversity in the action video. This paper proposes an Action Conditional Temporal Variational AutoEncoder (ACT-VAE) to improve motion prediction accuracy and capture movement diversity. ACT-VAE predicts pose sequences for an action clips from a single input image. It is implemented as a deep generative model that maintains temporal coherence according to the action category with a novel temporal modeling on latent space. Further, ACT-VAE is a general action sequence prediction framework. When connected with a plug-and-play Pose-to-Image (P2I) network, ACT-VAE can synthesize image sequences. Extensive experiments bear out our approach can predict accurate pose and synthesize realistic image sequences, surpassing state-of-the-art approaches. Compared to existing methods, ACT-VAE improves model accuracy and preserves diversity.

arXiv:2108.04103

End-to-end Neural Video Coding Using a Compound Spatiotemporal Representation

Recent years have witnessed rapid advances in learnt video coding. Most algorithms have solely relied on the vector-based motion representation and resampling (e.g., optical flow based bilinear sampling) for exploiting the inter frame redundancy. In spite of the great success of adaptive kernel-based resampling (e.g., adaptive convolutions and deformable convolutions) in video prediction for uncompressed videos, integrating such approaches with rate-distortion optimization for inter frame coding has been less successful. Recognizing that each resampling solution offers unique advantages in regions with different motion and texture characteristics, we propose a hybrid motion compensation (HMC) method that adaptively combines the predictions generated by these two approaches. Specifically, we generate a compound spatiotemporal representation (CSTR) through a recurrent information aggregation (RIA) module using information from the current and multiple past frames. We further design a one-to-many decoder pipeline to generate multiple predictions from the CSTR, including vector-based resampling, adaptive kernel-based resampling, compensation mode selection maps and texture enhancements, and combines them adaptively to achieve more accurate inter prediction. Experiments show that our proposed inter coding system can provide better motion-compensated prediction and is more robust to occlusions and complex motions. Together with jointly trained intra coder and residual coder, the overall learnt hybrid coder yields the state-of-the-art coding efficiency in low-delay scenario, compared to the traditional H.264/AVC and H.265/HEVC, as well as recently published learning-based methods, in terms of both PSNR and MS-SSIM metrics.

arXiv:2108.02760공식 코드 · Papers with Code

SLAMP: Stochastic Latent Appearance and Motion Prediction

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.

arXiv:2107.13170공식 코드 · Papers with Code

Accurate Grid Keypoint Learning for Efficient Video Prediction

Video prediction methods generally consume substantial computing resources in training and deployment, among which keypoint-based approaches show promising improvement in efficiency by simplifying dense image prediction to light keypoint prediction. However, keypoint locations are often modeled only as continuous coordinates, so noise from semantically insignificant deviations in videos easily disrupt learning stability, leading to inaccurate keypoint modeling. In this paper, we design a new grid keypoint learning framework, aiming at a robust and explainable intermediate keypoint representation for long-term efficient video prediction. We have two major technical contributions. First, we detect keypoints by jumping among candidate locations in our raised grid space and formulate a condensation loss to encourage meaningful keypoints with strong representative capability. Second, we introduce a 2D binary map to represent the detected grid keypoints and then suggest propagating keypoint locations with stochasticity by selecting entries in the discrete grid space, thus preserving the spatial structure of keypoints in the longterm horizon for better future frame generation. Extensive experiments verify that our method outperforms the state-ofthe-art stochastic video prediction methods while saves more than 98% of computing resources. We also demonstrate our method on a robotic-assisted surgery dataset with promising results. Our code is available at https://github.com/xjgaocs/Grid-Keypoint-Learning.

arXiv:2107.10068

From Single to Multiple: Leveraging Multi-level Prediction Spaces for Video Forecasting

Despite video forecasting has been a widely explored topic in recent years, the mainstream of the existing work still limits their models with a single prediction space but completely neglects the way to leverage their model with multi-prediction spaces. This work fills this gap. For the first time, we deeply study numerous strategies to perform video forecasting in multi-prediction spaces and fuse their results together to boost performance. The prediction in the pixel space usually lacks the ability to preserve the semantic and structure content of the video however the prediction in the high-level feature space is prone to generate errors in the reduction and recovering process. Therefore, we build a recurrent connection between different feature spaces and incorporate their generations in the upsampling process. Rather surprisingly, this simple idea yields a much more significant performance boost than PhyDNet (performance improved by 32.1% MAE on MNIST-2 dataset, and 21.4% MAE on KTH dataset). Both qualitative and quantitative evaluations on four datasets demonstrate the generalization ability and effectiveness of our approach. We show that our model significantly reduces the troublesome distortions and blurry artifacts and brings remarkable improvements to the accuracy in long term video prediction. The code will be released soon.

arXiv:2107.09047공식 코드 · Papers with Code

Know Thyself: Transferable Visual Control Policies Through Robot-Awareness

Training visual control policies from scratch on a new robot typically requires generating large amounts of robot-specific data. How might we leverage data previously collected on another robot to reduce or even completely remove this need for robot-specific data? We propose a "robot-aware control" paradigm that achieves this by exploiting readily available knowledge about the robot. We then instantiate this in a robot-aware model-based RL policy by training modular dynamics models that couple a transferable, robot-aware world dynamics module with a robot-specific, potentially analytical, robot dynamics module. This also enables us to set up visual planning costs that separately consider the robot agent and the world. Our experiments on tabletop manipulation tasks with simulated and real robots demonstrate that these plug-in improvements dramatically boost the transferability of visual model-based RL policies, even permitting zero-shot transfer of visual manipulation skills onto new robots. Project website: https://www.seas.upenn.edu/~hued/rac