PyTorchKR Papers

최신 논문

총 358편
태그·기간 등 상세 필터

카테고리 탐색

로그인 후 이 태그 구독

arXiv:2312.03406공식 코드 · Papers with Code

Does Vector Quantization Fail in Spatio-Temporal Forecasting? Exploring a Differentiable Sparse Soft-Vector Quantization Approach

Spatio-temporal forecasting is crucial in various fields and requires a careful balance between identifying subtle patterns and filtering out noise. Vector quantization (VQ) appears well-suited for this purpose, as it quantizes input vectors into a set of codebook vectors or patterns. Although VQ has shown promise in various computer vision tasks, it surprisingly falls short in enhancing the accuracy of spatio-temporal forecasting. We attribute this to two main issues: inaccurate optimization due to non-differentiability and limited representation power in hard-VQ. To tackle these challenges, we introduce Differentiable Sparse Soft-Vector Quantization (SVQ), the first VQ method to enhance spatio-temporal forecasting. SVQ balances detail preservation with noise reduction, offering full differentiability and a solid foundation in sparse regression. Our approach employs a two-layer MLP and an extensive codebook to streamline the sparse regression process, significantly cutting computational costs while simplifying training and improving performance. Empirical studies on five spatio-temporal benchmark datasets show SVQ achieves state-of-the-art results, including a 7.9% improvement on the WeatherBench-S temperature dataset and an average mean absolute error reduction of 9.4% in video prediction benchmarks (Human3.6M, KTH, and KittiCaltech), along with a 17.3% enhancement in image quality (LPIPS). Code is publicly available at https://github.com/Pachark/SVQ-Forecasting.

arXiv:2312.01699공식 코드 · Papers with Code

Rethinking Urban Mobility Prediction: A Super-Multivariate Time Series Forecasting Approach

Long-term urban mobility predictions play a crucial role in the effective management of urban facilities and services. Conventionally, urban mobility data has been structured as spatiotemporal videos, treating longitude and latitude grids as fundamental pixels. Consequently, video prediction methods, relying on Convolutional Neural Networks (CNNs) and Vision Transformers (ViTs), have been instrumental in this domain. In our research, we introduce a fresh perspective on urban mobility prediction. Instead of oversimplifying urban mobility data as traditional video data, we regard it as a complex multivariate time series. This perspective involves treating the time-varying values of each grid in each channel as individual time series, necessitating a thorough examination of temporal dynamics, cross-variable correlations, and frequency-domain insights for precise and reliable predictions. To address this challenge, we present the Super-Multivariate Urban Mobility Transformer (SUMformer), which utilizes a specially designed attention mechanism to calculate temporal and cross-variable correlations and reduce computational costs stemming from a large number of time series. SUMformer also employs low-frequency filters to extract essential information for long-term predictions. Furthermore, SUMformer is structured with a temporal patch merge mechanism, forming a hierarchical framework that enables the capture of multi-scale correlations. Consequently, it excels in urban mobility pattern modeling and long-term prediction, outperforming current state-of-the-art methods across three real-world datasets.

arXiv:2311.11289공식 코드 · Papers with Code

Pair-wise Layer Attention with Spatial Masking for Video Prediction

Video prediction yields future frames by employing the historical frames and has exhibited its great potential in many applications, e.g., meteorological prediction, and autonomous driving. Previous works often decode the ultimate high-level semantic features to future frames without texture details, which deteriorates the prediction quality. Motivated by this, we develop a Pair-wise Layer Attention (PLA) module to enhance the layer-wise semantic dependency of the feature maps derived from the U-shape structure in Translator, by coupling low-level visual cues and high-level features. Hence, the texture details of predicted frames are enriched. Moreover, most existing methods capture the spatiotemporal dynamics by Translator, but fail to sufficiently utilize the spatial features of Encoder. This inspires us to design a Spatial Masking (SM) module to mask partial encoding features during pretraining, which adds the visibility of remaining feature pixels by Decoder. To this end, we present a Pair-wise Layer Attention with Spatial Masking (PLA-SM) framework for video prediction to capture the spatiotemporal dynamics, which reflect the motion trend. Extensive experiments and rigorous ablation studies on five benchmarks demonstrate the advantages of the proposed approach. The code is available at GitHub.

arXiv:2311.11683

SIAM: A Simple Alternating Mixer for Video Prediction

Video prediction, predicting future frames from the previous ones, has broad applications such as autonomous driving and weather forecasting. Existing state-of-the-art methods typically focus on extracting either spatial, temporal, or spatiotemporal features from videos. Different feature focuses, resulting from different network architectures, may make the resultant models excel at some video prediction tasks but perform poorly on others. Towards a more generic video prediction solution, we explicitly model these features in a unified encoder-decoder framework and propose a novel simple alternating Mixer (SIAM). The novelty of SIAM lies in the design of dimension alternating mixing (DaMi) blocks, which can model spatial, temporal, and spatiotemporal features through alternating the dimensions of the feature maps. Extensive experimental results demonstrate the superior performance of the proposed SIAM on four benchmark video datasets covering both synthetic and real-world scenarios.

arXiv:2310.20700

SEINE: Short-to-Long Video Diffusion Model for Generative Transition and Prediction

Recently video generation has achieved substantial progress with realistic results. Nevertheless, existing AI-generated videos are usually very short clips ("shot-level") depicting a single scene. To deliver a coherent long video ("story-level"), it is desirable to have creative transition and prediction effects across different clips. This paper presents a short-to-long video diffusion model, SEINE, that focuses on generative transition and prediction. The goal is to generate high-quality long videos with smooth and creative transitions between scenes and varying lengths of shot-level videos. Specifically, we propose a random-mask video diffusion model to automatically generate transitions based on textual descriptions. By providing the images of different scenes as inputs, combined with text-based control, our model generates transition videos that ensure coherence and visual quality. Furthermore, the model can be readily extended to various tasks such as image-to-video animation and autoregressive video prediction. To conduct a comprehensive evaluation of this new generative task, we propose three assessing criteria for smooth and creative transition: temporal consistency, semantic similarity, and video-text semantic alignment. Extensive experiments validate the effectiveness of our approach over existing methods for generative transition and prediction, enabling the creation of story-level long videos. Project page: https://vchitect.github.io/SEINE-project/ .

arXiv:2310.12975

Variational Inference for SDEs Driven by Fractional Noise

We present a novel variational framework for performing inference in (neural) stochastic differential equations (SDEs) driven by Markov-approximate fractional Brownian motion (fBM). SDEs offer a versatile tool for modeling real-world continuous-time dynamic systems with inherent noise and randomness. Combining SDEs with the powerful inference capabilities of variational methods, enables the learning of representative function distributions through stochastic gradient descent. However, conventional SDEs typically assume the underlying noise to follow a Brownian motion (BM), which hinders their ability to capture long-term dependencies. In contrast, fractional Brownian motion (fBM) extends BM to encompass non-Markovian dynamics, but existing methods for inferring fBM parameters are either computationally demanding or statistically inefficient. In this paper, building upon the Markov approximation of fBM, we derive the evidence lower bound essential for efficient variational inference of posterior path measures, drawing from the well-established field of stochastic analysis. Additionally, we provide a closed-form expression to determine optimal approximation coefficients. Furthermore, we propose the use of neural networks to learn the drift, diffusion and control terms within our variational posterior, leading to the variational training of neural-SDEs. In this framework, we also optimize the Hurst index, governing the nature of our fractional noise. Beyond validation on synthetic data, we contribute a novel architecture for variational latent video prediction,-an approach that, to the best of our knowledge, enables the first variational neural-SDE application to video perception.

arXiv:2310.05737

Language Model Beats Diffusion -- Tokenizer is Key to Visual Generation

While Large Language Models (LLMs) are the dominant models for generative tasks in language, they do not perform as well as diffusion models on image and video generation. To effectively use LLMs for visual generation, one crucial component is the visual tokenizer that maps pixel-space inputs to discrete tokens appropriate for LLM learning. In this paper, we introduce MAGVIT-v2, a video tokenizer designed to generate concise and expressive tokens for both videos and images using a common token vocabulary. Equipped with this new tokenizer, we show that LLMs outperform diffusion models on standard image and video generation benchmarks including ImageNet and Kinetics. In addition, we demonstrate that our tokenizer surpasses the previously top-performing video tokenizer on two more tasks: (1) video compression comparable to the next-generation video codec (VCC) according to human evaluations, and (2) learning effective representations for action recognition tasks.

arXiv:2308.16154공식 코드 · Papers with Code

MMVP: Motion-Matrix-based Video Prediction

A central challenge of video prediction lies where the system has to reason the objects' future motions from image frames while simultaneously maintaining the consistency of their appearances across frames. This work introduces an end-to-end trainable two-stream video prediction framework, Motion-Matrix-based Video Prediction (MMVP), to tackle this challenge. Unlike previous methods that usually handle motion prediction and appearance maintenance within the same set of modules, MMVP decouples motion and appearance information by constructing appearance-agnostic motion matrices. The motion matrices represent the temporal similarity of each and every pair of feature patches in the input frames, and are the sole input of the motion prediction module in MMVP. This design improves video prediction in both accuracy and efficiency, and reduces the model size. Results of extensive experiments demonstrate that MMVP outperforms state-of-the-art systems on public data sets by non-negligible large margins (about 1 db in PSNR, UCF Sports) in significantly smaller model sizes (84% the size or smaller).

arXiv:2308.09891공식 코드 · Papers with Code

SwinLSTM:Improving Spatiotemporal Prediction Accuracy using Swin Transformer and LSTM

Integrating CNNs and RNNs to capture spatiotemporal dependencies is a prevalent strategy for spatiotemporal prediction tasks. However, the property of CNNs to learn local spatial information decreases their efficiency in capturing spatiotemporal dependencies, thereby limiting their prediction accuracy. In this paper, we propose a new recurrent cell, SwinLSTM, which integrates Swin Transformer blocks and the simplified LSTM, an extension that replaces the convolutional structure in ConvLSTM with the self-attention mechanism. Furthermore, we construct a network with SwinLSTM cell as the core for spatiotemporal prediction. Without using unique tricks, SwinLSTM outperforms state-of-the-art methods on Moving MNIST, Human3.6m, TaxiBJ, and KTH datasets. In particular, it exhibits a significant improvement in prediction accuracy compared to ConvLSTM. Our competitive experimental results demonstrate that learning global spatial dependencies is more advantageous for models to capture spatiotemporal dependencies. We hope that SwinLSTM can serve as a solid baseline to promote the advancement of spatiotemporal prediction accuracy. The codes are publicly available at https://github.com/SongTang-x/SwinLSTM.

arXiv:2308.07783

Future Video Prediction from a Single Frame for Video Anomaly Detection

Video anomaly detection (VAD) is an important but challenging task in computer vision. The main challenge rises due to the rarity of training samples to model all anomaly cases. Hence, semi-supervised anomaly detection methods have gotten more attention, since they focus on modeling normals and they detect anomalies by measuring the deviations from normal patterns. Despite impressive advances of these methods in modeling normal motion and appearance, long-term motion modeling has not been effectively explored so far. Inspired by the abilities of the future frame prediction proxy-task, we introduce the task of future video prediction from a single frame, as a novel proxy-task for video anomaly detection. This proxy-task alleviates the challenges of previous methods in learning longer motion patterns. Moreover, we replace the initial and future raw frames with their corresponding semantic segmentation map, which not only makes the method aware of object class but also makes the prediction task less complex for the model. Extensive experiments on the benchmark datasets (ShanghaiTech, UCSD-Ped1, and UCSD-Ped2) show the effectiveness of the method and the superiority of its performance compared to SOTA prediction-based VAD methods.

arXiv:2307.06701

S-HR-VQVAE: Sequential Hierarchical Residual Learning Vector Quantized Variational Autoencoder for Video Prediction

We address the video prediction task by putting forth a novel model that combines (i) a novel hierarchical residual learning vector quantized variational autoencoder (HR-VQVAE), and (ii) a novel autoregressive spatiotemporal predictive model (AST-PM). We refer to this approach as a sequential hierarchical residual learning vector quantized variational autoencoder (S-HR-VQVAE). By leveraging the intrinsic capabilities of HR-VQVAE at modeling still images with a parsimonious representation, combined with the AST-PM's ability to handle spatiotemporal information, S-HR-VQVAE can better deal with major challenges in video prediction. These include learning spatiotemporal information, handling high dimensional data, combating blurry prediction, and implicit modeling of physical characteristics. Extensive experimental results on four challenging tasks, namely KTH Human Action, TrafficBJ, Human3.6M, and Kitti, demonstrate that our model compares favorably against state-of-the-art video prediction techniques both in quantitative and qualitative evaluations despite a much smaller model size. Finally, we boost S-HR-VQVAE by proposing a novel training method to jointly estimate the HR-VQVAE and AST-PM parameters.

arXiv:2306.15852

Action-conditioned Deep Visual Prediction with RoAM, a new Indoor Human Motion Dataset for Autonomous Robots

With the increasing adoption of robots across industries, it is crucial to focus on developing advanced algorithms that enable robots to anticipate, comprehend, and plan their actions effectively in collaboration with humans. We introduce the Robot Autonomous Motion (RoAM) video dataset, which is collected with a custom-made turtlebot3 Burger robot in a variety of indoor environments recording various human motions from the robot's ego-vision. The dataset also includes synchronized records of the LiDAR scan and all control actions taken by the robot as it navigates around static and moving human agents. The unique dataset provides an opportunity to develop and benchmark new visual prediction frameworks that can predict future image frames based on the action taken by the recording agent in partially observable scenarios or cases where the imaging sensor is mounted on a moving platform. We have benchmarked the dataset on our novel deep visual prediction framework called ACPNet where the approximated future image frames are also conditioned on action taken by the robot and demonstrated its potential for incorporating robot dynamics into the video prediction paradigm for mobile robotics and autonomous navigation research.

arXiv:2306.15668

Physion++: Evaluating Physical Scene Understanding that Requires Online Inference of Different Physical Properties

General physical scene understanding requires more than simply localizing and recognizing objects -- it requires knowledge that objects can have different latent properties (e.g., mass or elasticity), and that those properties affect the outcome of physical events. While there has been great progress in physical and video prediction models in recent years, benchmarks to test their performance typically do not require an understanding that objects have individual physical properties, or at best test only those properties that are directly observable (e.g., size or color). This work proposes a novel dataset and benchmark, termed Physion++, that rigorously evaluates visual physical prediction in artificial systems under circumstances where those predictions rely on accurate estimates of the latent physical properties of objects in the scene. Specifically, we test scenarios where accurate prediction relies on estimates of properties such as mass, friction, elasticity, and deformability, and where the values of those properties can only be inferred by observing how objects move and interact with other objects or fluids. We evaluate the performance of a number of state-of-the-art prediction models that span a variety of levels of learning vs. built-in knowledge, and compare that performance to a set of human predictions. We find that models that have been trained using standard regimes and datasets do not spontaneously learn to make inferences about latent properties, but also that models that encode objectness and physical states tend to make better predictions. However, there is still a huge gap between all models and human performance, and all models' predictions correlate poorly with those made by humans, suggesting that no state-of-the-art model is learning to make physical predictions in a human-like way. Project page: https://dingmyu.github.io/physion_v2/

arXiv:2306.12545공식 코드 · Papers with Code

Neural Multigrid Memory For Computational Fluid Dynamics

Turbulent flow simulation plays a crucial role in various applications, including aircraft and ship design, industrial process optimization, and weather prediction. In this paper, we propose an advanced data-driven method for simulating turbulent flow, representing a significant improvement over existing approaches. Our methodology combines the strengths of Video Prediction Transformer (VPTR) (Ye & Bilodeau, 2022) and Multigrid Architecture (MgConv, MgResnet) (Ke et al., 2017). VPTR excels in capturing complex spatiotemporal dependencies and handling large input data, making it a promising choice for turbulent flow prediction. Meanwhile, Multigrid Architecture utilizes multiple grids with different resolutions to capture the multiscale nature of turbulent flows, resulting in more accurate and efficient simulations. Through our experiments, we demonstrate the effectiveness of our proposed approach, named MGxTransformer, in accurately predicting velocity, temperature, and turbulence intensity for incompressible turbulent flows across various geometries and flow conditions. Our results exhibit superior accuracy compared to other baselines, while maintaining computational efficiency. Our implementation in PyTorch is available publicly at https://github.com/Combi2k2/MG-Turbulent-Flow

arXiv:2306.10346공식 코드 · Papers with Code

Fast Fourier Inception Networks for Occluded Video Prediction

Video prediction is a pixel-level task that generates future frames by employing the historical frames. There often exist continuous complex motions, such as object overlapping and scene occlusion in video, which poses great challenges to this task. Previous works either fail to well capture the long-term temporal dynamics or do not handle the occlusion masks. To address these issues, we develop the fully convolutional Fast Fourier Inception Networks for video prediction, termed \textit{FFINet}, which includes two primary components, \ie, the occlusion inpainter and the spatiotemporal translator. The former adopts the fast Fourier convolutions to enlarge the receptive field, such that the missing areas (occlusion) with complex geometric structures are filled by the inpainter. The latter employs the stacked Fourier transform inception module to learn the temporal evolution by group convolutions and the spatial movement by channel-wise Fourier convolutions, which captures both the local and the global spatiotemporal features. This encourages generating more realistic and high-quality future frames. To optimize the model, the recovery loss is imposed to the objective, \ie, minimizing the mean square error between the ground-truth frame and the recovery frame. Both quantitative and qualitative experimental results on five benchmarks, including Moving MNIST, TaxiBJ, Human3.6M, Caltech Pedestrian, and KTH, have demonstrated the superiority of the proposed approach. Our code is available at GitHub.

arXiv:2306.11682공식 코드 · Papers with Code

SkyGPT: Probabilistic Short-term Solar Forecasting Using Synthetic Sky Videos from Physics-constrained VideoGPT

In recent years, deep learning-based solar forecasting using all-sky images has emerged as a promising approach for alleviating uncertainty in PV power generation. However, the stochastic nature of cloud movement remains a major challenge for accurate and reliable solar forecasting. With the recent advances in generative artificial intelligence, the synthesis of visually plausible yet diversified sky videos has potential for aiding in forecasts. In this study, we introduce \emph{SkyGPT}, a physics-informed stochastic video prediction model that is able to generate multiple possible future images of the sky with diverse cloud motion patterns, by using past sky image sequences as input. Extensive experiments and comparison with benchmark video prediction models demonstrate the effectiveness of the proposed model in capturing cloud dynamics and generating future sky images with high realism and diversity. Furthermore, we feed the generated future sky images from the video prediction models for 15-minute-ahead probabilistic solar forecasting for a 30-kW roof-top PV system, and compare it with an end-to-end deep learning baseline model SUNSET and a smart persistence model. Better PV output prediction reliability and sharpness is observed by using the predicted sky images generated with SkyGPT compared with other benchmark models, achieving a continuous ranked probability score (CRPS) of 2.81 (13\% better than SUNSET and 23\% better than smart persistence) and a Winkler score of 26.70 for the test set. Although an arbitrary number of futures can be generated from a historical sky image sequence, the results suggest that 10 future scenarios is a good choice that balances probabilistic solar forecasting performance and computational cost.

arXiv:2306.05957공식 코드 · Papers with Code

DDLP: Unsupervised Object-Centric Video Prediction with Deep Dynamic Latent Particles

We propose a new object-centric video prediction algorithm based on the deep latent particle (DLP) representation. In comparison to existing slot- or patch-based representations, DLPs model the scene using a set of keypoints with learned parameters for properties such as position and size, and are both efficient and interpretable. Our method, deep dynamic latent particles (DDLP), yields state-of-the-art object-centric video prediction results on several challenging datasets. The interpretable nature of DDLP allows us to perform ``what-if'' generation -- predict the consequence of changing properties of objects in the initial frames, and DLP's compact structure enables efficient diffusion-based unconditional video generation. Videos, code and pre-trained models are available: https://taldatech.github.io/ddlp-web

arXiv:2306.02562공식 코드 · Papers with Code

Video Diffusion Models with Local-Global Context Guidance

Diffusion models have emerged as a powerful paradigm in video synthesis tasks including prediction, generation, and interpolation. Due to the limitation of the computational budget, existing methods usually implement conditional diffusion models with an autoregressive inference pipeline, in which the future fragment is predicted based on the distribution of adjacent past frames. However, only the conditions from a few previous frames can't capture the global temporal coherence, leading to inconsistent or even outrageous results in long-term video prediction. In this paper, we propose a Local-Global Context guided Video Diffusion model (LGC-VD) to capture multi-perception conditions for producing high-quality videos in both conditional/unconditional settings. In LGC-VD, the UNet is implemented with stacked residual blocks with self-attention units, avoiding the undesirable computational cost in 3D Conv. We construct a local-global context guidance strategy to capture the multi-perceptual embedding of the past fragment to boost the consistency of future prediction. Furthermore, we propose a two-stage training strategy to alleviate the effect of noisy frames for more stable predictions. Our experiments demonstrate that the proposed method achieves favorable performance on video prediction, interpolation, and unconditional video generation. We release code at https://github.com/exisas/LGC-VD.

arXiv:2305.13903공식 코드 · Papers with Code

Let's Think Frame by Frame with VIP: A Video Infilling and Prediction Dataset for Evaluating Video Chain-of-Thought

Despite exciting recent results showing vision-language systems' capacity to reason about images using natural language, their capacity for video reasoning remains under-explored. We motivate framing video reasoning as the sequential understanding of a small number of keyframes, thereby leveraging the power and robustness of vision-language while alleviating the computational complexities of processing videos. To evaluate this novel application, we introduce VIP, an inference-time challenge dataset designed to explore models' reasoning capabilities through video chain-of-thought. Inspired by visually descriptive scene plays, we propose two formats for keyframe description: unstructured dense captions and structured scene descriptions that identify the focus, action, mood, objects, and setting (FAMOuS) of the keyframe. To evaluate video reasoning, we propose two tasks: Video Infilling and Video Prediction, which test abilities to generate multiple intermediate keyframes and predict future keyframes, respectively. We benchmark GPT-4, GPT-3, and VICUNA on VIP, demonstrate the performance gap in these complex video reasoning tasks, and encourage future work to prioritize language models for efficient and generalized video reasoning.

arXiv:2305.14343

Video Prediction Models as Rewards for Reinforcement Learning

Specifying reward signals that allow agents to learn complex behaviors is a long-standing challenge in reinforcement learning. A promising approach is to extract preferences for behaviors from unlabeled videos, which are widely available on the internet. We present Video Prediction Rewards (VIPER), an algorithm that leverages pretrained video prediction models as action-free reward signals for reinforcement learning. Specifically, we first train an autoregressive transformer on expert videos and then use the video prediction likelihoods as reward signals for a reinforcement learning agent. VIPER enables expert-level control without programmatic task rewards across a wide range of DMC, Atari, and RLBench tasks. Moreover, generalization of the video prediction model allows us to derive rewards for an out-of-distribution environment where no expert data is available, enabling cross-embodiment generalization for tabletop manipulation. We see our work as starting point for scalable reward specification from unlabeled videos that will benefit from the rapid advances in generative modeling. Source code and datasets are available on the project website: https://escontrela.me/viper