We propose a novel framework for the task of object-centric video prediction, i.e., extracting the compositional structure of a video sequence, as well as modeling objects dynamics and interactions from visual observations in order to predict the future object states, from which we can then generate subsequent video frames. With the goal of learning meaningful spatio-temporal object representations and accurately forecasting object states, we propose two novel object-centric video predictor (OCVP) transformer modules, which decouple the processing of temporal dynamics and object interactions, thus presenting an improved prediction performance. In our experiments, we show how our object-centric prediction framework utilizing our OCVP predictors outperforms object-agnostic video prediction models on two different datasets, while maintaining consistent and accurate object representations.
我们提出了一种新的框架,用于对象中心的视频预测任务,即从视频序列中抽取构成性结构,并基于视觉观察建模对象动态和交互,以预测未来对象状态,并从该状态中生成后续视频帧。为了实现学习有意义的空间时间对象表示以及准确预测对象状态的目标,我们提出了两个全新的对象中心视频预测(OCVP)Transformer模块,它们将时间动态处理与对象交互处理分离,从而提高了预测性能。在我们的实验中,我们展示了如何使用我们的OCVP预测器我们的对象中心预测框架在两个不同数据集上优于对象无关的视频预测模型,同时保持了一致性和准确的对象表示。
https://arxiv.org/abs/2302.11850
Prediction of dynamic environment is crucial to safe navigation of an autonomous vehicle. Urban traffic scenes are particularly challenging to forecast due to complex interactions between various dynamic agents, such as vehicles and vulnerable road users. Previous approaches have used egocentric occupancy grid maps to represent and predict dynamic environments. However, these predictions suffer from blurriness, loss of scene structure at turns, and vanishing of agents over longer prediction horizon. In this work, we propose a novel framework to make long-term predictions by representing the traffic scene in a fixed frame, referred as allo-centric occupancy grid. This allows for the static scene to remain fixed and to represent motion of the ego-vehicle on the grid like other agents'. We study the allo-centric grid prediction with different video prediction networks and validate the approach on the real-world Nuscenes dataset. The results demonstrate that the allo-centric grid representation significantly improves scene prediction, in comparison to the conventional ego-centric grid approach.
https://arxiv.org/abs/2301.04454
The task of video prediction and generation is known to be notoriously difficult, with the research in this area largely limited to short-term predictions. Though plagued with noise and stochasticity, videos consist of features that are organised in a spatiotemporal hierarchy, different features possessing different temporal dynamics. In this paper, we introduce Dynamic Latent Hierarchy (DLH) -- a deep hierarchical latent model that represents videos as a hierarchy of latent states that evolve over separate and fluid timescales. Each latent state is a mixture distribution with two components, representing the immediate past and the predicted future, causing the model to learn transitions only between sufficiently dissimilar states, while clustering temporally persistent states closer together. Using this unique property, DLH naturally discovers the spatiotemporal structure of a dataset and learns disentangled representations across its hierarchy. We hypothesise that this simplifies the task of modeling temporal dynamics of a video, improves the learning of long-term dependencies, and reduces error accumulation. As evidence, we demonstrate that DLH outperforms state-of-the-art benchmarks in video prediction, is able to better represent stochasticity, as well as to dynamically adjust its hierarchical and temporal structure. Our paper shows, among other things, how progress in representation learning can translate into progress in prediction tasks.
https://arxiv.org/abs/2212.14376
We are introducing a multi-scale predictive model for video prediction here, whose design is inspired by the "Predictive Coding" theories and "Coarse to Fine" approach. As a predictive coding model, it is updated by a combination of bottom-up and top-down information flows, which is different from traditional bottom-up training style. Its advantage is to reduce the dependence on input information and improve its ability to predict and generate images. Importantly, we achieve with a multi-scale approach -- higher level neurons generate coarser predictions (lower resolution), while the lower level generate finer predictions (higher resolution). This is different from the traditional predictive coding framework in which higher level predict the activity of neurons in lower level. To improve the predictive ability, we integrate an encoder-decoder network in the LSTM architecture and share the final encoded high-level semantic information between different levels. Additionally, since the output of each network level is an RGB image, a smaller LSTM hidden state can be used to retain and update the only necessary hidden information, avoiding being mapped to an overly discrete and complex space. In this way, we can reduce the difficulty of prediction and the computational overhead. Finally, we further explore the training strategies, to address the instability in adversarial training and mismatch between training and testing in long-term prediction. Code is available at this https URL.
https://arxiv.org/abs/2212.11642
Video prediction is a challenging computer vision task that has a wide range of applications. In this work, we present a new family of Transformer-based models for video prediction. Firstly, an efficient local spatial-temporal separation attention mechanism is proposed to reduce the complexity of standard Transformers. Then, a full autoregressive model, a partial autoregressive model and a non-autoregressive model are developed based on the new efficient Transformer. The partial autoregressive model has a similar performance with the full autoregressive model but a faster inference speed. The non-autoregressive model not only achieves a faster inference speed but also mitigates the quality degradation problem of the autoregressive counterparts, but it requires additional parameters and loss function for learning. Given the same attention mechanism, we conducted a comprehensive study to compare the proposed three video prediction variants. Experiments show that the proposed video prediction models are competitive with more complex state-of-the-art convolutional-LSTM based models. The source code is available at this https URL.
https://arxiv.org/abs/2212.06026
Existing state-of-the-art method for audio-visual conditioned video prediction uses the latent codes of the audio-visual frames from a multimodal stochastic network and a frame encoder to predict the next visual frame. However, a direct inference of per-pixel intensity for the next visual frame from the latent codes is extremely challenging because of the high-dimensional image space. To this end, we propose to decouple the audio-visual conditioned video prediction into motion and appearance modeling. The first part is the multimodal motion estimation module that learns motion information as optical flow from the given audio-visual clip. The second part is the context-aware refinement module that uses the predicted optical flow to warp the current visual frame into the next visual frame and refines it base on the given audio-visual context. Experimental results show that our method achieves competitive results on existing benchmarks.
https://arxiv.org/abs/2212.04679
The mainstream of the existing approaches for video prediction builds up their models based on a Single-In-Single-Out (SISO) architecture, which takes the current frame as input to predict the next frame in a recursive manner. This way often leads to severe performance degradation when they try to extrapolate a longer period of future, thus limiting the practical use of the prediction model. Alternatively, a Multi-In-Multi-Out (MIMO) architecture that outputs all the future frames at one shot naturally breaks the recursive manner and therefore prevents error accumulation. However, only a few MIMO models for video prediction are proposed and they only achieve inferior performance due to the date. The real strength of the MIMO model in this area is not well noticed and is largely under-explored. Motivated by that, we conduct a comprehensive investigation in this paper to thoroughly exploit how far a simple MIMO architecture can go. Surprisingly, our empirical studies reveal that a simple MIMO model can outperform the state-of-the-art work with a large margin much more than expected, especially in dealing with longterm error accumulation. After exploring a number of ways and designs, we propose a new MIMO architecture based on extending the pure Transformer with local spatio-temporal blocks and a new multi-output decoder, namely MIMO-VP, to establish a new standard in video prediction. We evaluate our model in four highly competitive benchmarks (Moving MNIST, Human3.6M, Weather, KITTI). Extensive experiments show that our model wins 1st place on all the benchmarks with remarkable performance gains and surpasses the best SISO model in all aspects including efficiency, quantity, and quality. We believe our model can serve as a new baseline to facilitate the future research of video prediction tasks. The code will be released.
https://arxiv.org/abs/2212.04655
We introduce a novel generative model for video prediction based on latent flow matching, an efficient alternative to diffusion-based models. In contrast to prior work that either incurs a high training cost by modeling the past through a memory state, as in recurrent neural networks, or limits the computational load by conditioning only on a predefined window of past frames, we efficiently and effectively take the past into account by conditioning at inference time only on a small random set of past frames at each integration step of the learned flow. Moreover, to enable the generation of high-resolution videos and speed up the training, we work in the latent space of a pretrained VQGAN. Furthermore, we propose to approximate the initial condition of the flow ODE with the previous noisy frame. This allows to reduce the number of integration steps and hence, speed up the sampling at inference time. We call our model Random frame conditional flow Integration for VidEo pRediction, or, in short, RIVER. We show that RIVER achieves superior or on par performance compared to prior work on common video prediction benchmarks.
https://arxiv.org/abs/2211.14575
Generating a video given the first several static frames is challenging as it anticipates reasonable future frames with temporal coherence. Besides video prediction, the ability to rewind from the last frame or infilling between the head and tail is also crucial, but they have rarely been explored for video completion. Since there could be different outcomes from the hints of just a few frames, a system that can follow natural language to perform video completion may significantly improve controllability. Inspired by this, we introduce a novel task, text-guided video completion (TVC), which requests the model to generate a video from partial frames guided by an instruction. We then propose Multimodal Masked Video Generation (MMVG) to address this TVC task. During training, MMVG discretizes the video frames into visual tokens and masks most of them to perform video completion from any time point. At inference time, a single MMVG model can address all 3 cases of TVC, including video prediction, rewind, and infilling, by applying corresponding masking conditions. We evaluate MMVG in various video scenarios, including egocentric, animation, and gaming. Extensive experimental results indicate that MMVG is effective in generating high-quality visual appearances with text guidance for TVC.
https://arxiv.org/abs/2211.12824
In this paper, we introduce 3D-CSL, a compact pipeline for Near-Duplicate Video Retrieval (NDVR), and explore a novel self-supervised learning strategy for video similarity learning. Most previous methods only extract video spatial features from frames separately and then design kinds of complex mechanisms to learn the temporal correlations among frame features. However, parts of spatiotemporal dependencies have already been lost. To address this, our 3D-CSL extracts global spatiotemporal dependencies in videos end-to-end with a 3D transformer and find a good balance between efficiency and effectiveness by matching on clip-level. Furthermore, we propose a two-stage self-supervised similarity learning strategy to optimize the entire network. Firstly, we propose PredMAE to pretrain the 3D transformer with video prediction task; Secondly, ShotMix, a novel video-specific augmentation, and FCS loss, a novel triplet loss, are proposed further promote the similarity learning results. The experiments on FIVR-200K and CC_WEB_VIDEO demonstrate the superiority and reliability of our method, which achieves the state-of-the-art performance on clip-level NDVR.
https://arxiv.org/abs/2211.05352
Forecasting the state of vegetation in response to climate and weather events is a major challenge. Its implementation will prove crucial in predicting crop yield, forest damage, or more generally the impact on ecosystems services relevant for socio-economic functioning, which if absent can lead to humanitarian disasters. Vegetation status depends on weather and environmental conditions that modulate complex ecological processes taking place at several timescales. Interactions between vegetation and different environmental drivers express responses at instantaneous but also time-lagged effects, often showing an emerging spatial context at landscape and regional scales. We formulate the land surface forecasting task as a strongly guided video prediction task where the objective is to forecast the vegetation developing at very fine resolution using topography and weather variables to guide the prediction. We use a Convolutional LSTM (ConvLSTM) architecture to address this task and predict changes in the vegetation state in Africa using Sentinel-2 satellite NDVI, having ERA5 weather reanalysis, SMAP satellite measurements, and topography (DEM of SRTMv4.1) as variables to guide the prediction. Ours results highlight how ConvLSTM models can not only forecast the seasonal evolution of NDVI at high resolution, but also the differential impacts of weather anomalies over the baselines. The model is able to predict different vegetation types, even those with very high NDVI variability during target length, which is promising to support anticipatory actions in the context of drought-related disasters.
https://arxiv.org/abs/2210.13648
Left-ventricular ejection fraction (LVEF) is an important indicator of heart failure. Existing methods for LVEF estimation from video require large amounts of annotated data to achieve high performance, e.g. using 10,030 labeled echocardiogram videos to achieve mean absolute error (MAE) of 4.10. Labeling these videos is time-consuming however and limits potential downstream applications to other heart diseases. This paper presents the first semi-supervised approach for LVEF prediction. Unlike general video prediction tasks, LVEF prediction is specifically related to changes in the left ventricle (LV) in echocardiogram videos. By incorporating knowledge learned from predicting LV segmentations into LVEF regression, we can provide additional context to the model for better predictions. To this end, we propose a novel Cyclical Self-Supervision (CSS) method for learning video-based LV segmentation, which is motivated by the observation that the heartbeat is a cyclical process with temporal repetition. Prediction masks from our segmentation model can then be used as additional input for LVEF regression to provide spatial context for the LV region. We also introduce teacher-student distillation to distill the information from LV segmentation masks into an end-to-end LVEF regression model that only requires video inputs. Results show our method outperforms alternative semi-supervised methods and can achieve MAE of 4.17, which is competitive with state-of-the-art supervised performance, using half the number of labels. Validation on an external dataset also shows improved generalization ability from using our method.
https://arxiv.org/abs/2210.11291
This paper presents two variations of a novel stochastic prediction algorithm that enables mobile robots to accurately and robustly predict the future state of complex dynamic scenes, such as environments full of people. The proposed algorithm uses a variational autoencoder-based neural network to predict a range of possible future states of the environment. The algorithm takes full advantage of the motion of the robot itself, the motion of dynamic objects, and the geometry of static objects in the scene to improve prediction accuracy. Three different datasets collected by different robot models are used to demonstrate that the proposed algorithm is able to achieve smaller absolute error, higher structure similarity, and higher tracking accuracy than state-of-the-art prediction algorithms for video prediction tasks. Implementations of both proposed stochastic prediction algorithms are available open source at this https URL.
https://arxiv.org/abs/2210.08577
Understanding dynamics from visual observations is a challenging problem that requires disentangling individual objects from the scene and learning their interactions. While recent object-centric models can successfully decompose a scene into objects, modeling their dynamics effectively still remains a challenge. We address this problem by introducing SlotFormer -- a Transformer-based autoregressive model operating on learned object-centric representations. Given a video clip, our approach reasons over object features to model spatio-temporal relationships and predicts accurate future object states. In this paper, we successfully apply SlotFormer to perform video prediction on datasets with complex object interactions. Moreover, the unsupervised SlotFormer's dynamics model can be used to improve the performance on supervised downstream tasks, such as Visual Question Answering (VQA), and goal-conditioned planning. Compared to past works on dynamics modeling, our method achieves significantly better long-term synthesis of object dynamics, while retaining high quality visual generation. Besides, SlotFormer enables VQA models to reason about the future without object-level labels, even outperforming counterparts that use ground-truth annotations. Finally, we show its ability to serve as a world model for model-based planning, which is competitive with methods designed specifically for such tasks.
https://arxiv.org/abs/2210.05861
We propose a unified model for multiple conditional video synthesis tasks, including video prediction and video frame interpolation. We show that conditional video synthesis can be formulated as a neural process, which maps input spatio-temporal coordinates to target pixel values given context spatio-temporal coordinates and pixels values. Specifically, we feed an implicit neural representations of coordinates into a Transformer-based non-autoregressive conditional video synthesis model. Our task-specific models outperform previous work for video interpolation on multiple datasets and reach a competitive performance with the state-of-the-art models for video prediction. Importantly, the model is able to interpolate or predict with an arbitrary high frame rate, i.e., continuous synthesis. Our source code is available at \url{this https URL}.
https://arxiv.org/abs/2210.05810
Cognitive planning is the structural decomposition of complex tasks into a sequence of future behaviors. In the computational setting, performing cognitive planning entails grounding plans and concepts in one or more modalities in order to leverage them for low level control. Since real-world tasks are often described in natural language, we devise a cognitive planning algorithm via language-guided video prediction. Current video prediction models do not support conditioning on natural language instructions. Therefore, we propose a new video prediction architecture which leverages the power of pre-trained transformers.The network is endowed with the ability to ground concepts based on natural language input with generalization to unseen objects. We demonstrate the effectiveness of this approach on a new simulation dataset, where each task is defined by a high-level action described in natural language. Our experiments compare our method again stone video generation baseline without planning or action grounding and showcase significant improvements. Our ablation studies highlight an improved generalization to unseen objects that natural language embeddings offer to concept grounding ability, as well as the importance of planning towards visual "imagination" of a task.
https://arxiv.org/abs/2210.03825
Current video generation models usually convert signals indicating appearance and motion received from inputs (e.g., image, text) or latent spaces (e.g., noise vectors) into consecutive frames, fulfilling a stochastic generation process for the uncertainty introduced by latent code sampling. However, this generation pattern lacks deterministic constraints for both appearance and motion, leading to uncontrollable and undesirable outcomes. To this end, we propose a new task called Text-driven Video Prediction (TVP). Taking the first frame and text caption as inputs, this task aims to synthesize the following frames. Specifically, appearance and motion components are provided by the image and caption separately. The key to addressing the TVP task depends on fully exploring the underlying motion information in text descriptions, thus facilitating plausible video generation. In fact, this task is intrinsically a cause-and-effect problem, as the text content directly influences the motion changes of frames. To investigate the capability of text in causal inference for progressive motion information, our TVP framework contains a Text Inference Module (TIM), producing step-wise embeddings to regulate motion inference for subsequent frames. In particular, a refinement mechanism incorporating global motion semantics guarantees coherent generation. Extensive experiments are conducted on Something-Something V2 and Single Moving MNIST datasets. Experimental results demonstrate that our model achieves better results over other baselines, verifying the effectiveness of the proposed framework.
https://arxiv.org/abs/2210.02872
Generating long, temporally consistent video remains an open challenge in video generation. Primarily due to computational limitations, most prior methods limit themselves to training on a small subset of frames that are then extended to generate longer videos through a sliding window fashion. Although these techniques may produce sharp videos, they have difficulty retaining long-term temporal consistency due to their limited context length. In this work, we present Temporally Consistent Video Transformer (TECO), a vector-quantized latent dynamics video prediction model that learns compressed representations to efficiently condition on long videos of hundreds of frames during both training and generation. We use a MaskGit prior for dynamics prediction which enables both sharper and faster generations compared to prior work. Our experiments show that TECO outperforms SOTA baselines in a variety of video prediction benchmarks ranging from simple mazes in DMLab, large 3D worlds in Minecraft, and complex real-world videos from Kinetics-600. In addition, to better understand the capabilities of video prediction models in modeling temporal consistency, we introduce several challenging video prediction tasks consisting of agents randomly traversing 3D scenes of varying difficulty. This presents a challenging benchmark for video prediction in partially observable environments where a model must understand what parts of the scenes to re-create versus invent depending on its past observations or generations. Generated videos are available at this https URL
https://arxiv.org/abs/2210.02396
For autonomous skill acquisition, robots have to learn about the physical rules governing the 3D world dynamics from their own past experience to predict and reason about plausible future outcomes. To this end, we propose a transformation-based 3D video prediction (T3VIP) approach that explicitly models the 3D motion by decomposing a scene into its object parts and predicting their corresponding rigid transformations. Our model is fully unsupervised, captures the stochastic nature of the real world, and the observational cues in image and point cloud domains constitute its learning signals. To fully leverage all the 2D and 3D observational signals, we equip our model with automatic hyperparameter optimization (HPO) to interpret the best way of learning from them. To the best of our knowledge, our model is the first generative model that provides an RGB-D video prediction of the future for a static camera. Our extensive evaluation with simulated and real-world datasets demonstrates that our formulation leads to interpretable 3D models that predict future depth videos while achieving on-par performance with 2D models on RGB video prediction. Moreover, we demonstrate that our model outperforms 2D baselines on visuomotor control. Videos, code, dataset, and pre-trained models are available at this http URL.
https://arxiv.org/abs/2209.11693
Video prediction is an important yet challenging problem; burdened with the tasks of generating future frames and learning environment dynamics. Recently, autoregressive latent video models have proved to be a powerful video prediction tool, by separating the video prediction into two sub-problems: pre-training an image generator model, followed by learning an autoregressive prediction model in the latent space of the image generator. However, successfully generating high-fidelity and high-resolution videos has yet to be seen. In this work, we investigate how to train an autoregressive latent video prediction model capable of predicting high-fidelity future frames with minimal modification to existing models, and produce high-resolution (256x256) videos. Specifically, we scale up prior models by employing a high-fidelity image generator (VQ-GAN) with a causal transformer model, and introduce additional techniques of top-k sampling and data augmentation to further improve video prediction quality. Despite the simplicity, the proposed method achieves competitive performance to state-of-the-art approaches on standard video prediction benchmarks with fewer parameters, and enables high-resolution video prediction on complex and large-scale datasets. Videos are available at this https URL.
https://arxiv.org/abs/2209.07143