Related papers: Simple Video Generation using Neural ODEs

Making predictions of future frames is a critical challenge in autonomous driving research. Most of the existing methods for video prediction attempt to generate future frames in simple and fixed scenes. In this paper, we propose a novel…

Deep generative neural networks have proven effective at both conditional and unconditional modeling of complex data distributions. Conditional generation enables interactive control, but creating new controls often requires expensive…

We introduce a new encoder-decoder GAN model, FutureGAN, that predicts future frames of a video sequence conditioned on a sequence of past frames. During training, the networks solely receive the raw pixel values as an input, without…

Despite the remarkable progress in deep generative models, synthesizing high-resolution and temporally coherent videos still remains a challenge due to their high-dimensionality and complex temporal dynamics along with large spatial…

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…

We address the problem of generating a 3D-consistent, navigable environment that is spatially grounded: a simulation of a real location. Existing video generative models can produce a plausible sequence that is consistent with a text (T2V)…

Video prediction is a challenging task. The quality of video frames from current state-of-the-art (SOTA) generative models tends to be poor and generalization beyond the training data is difficult. Furthermore, existing prediction…

Object permanence in humans is a fundamental cue that helps in understanding persistence of objects, even when they are fully occluded in the scene. Present day methods in object segmentation do not account for this amodal nature of the…

Diffusion models have emerged as a powerful generative method for synthesizing high-quality and diverse set of images. In this paper, we propose a video generation method based on diffusion models, where the effects of motion are modeled in…

Although deep learning has achieved appealing results on several machine learning tasks, most of the models are deterministic at inference, limiting their application to single-modal settings. We propose a novel general-purpose framework…

In a given scene, humans can often easily predict a set of immediate future events that might happen. However, generalized pixel-level anticipation in computer vision systems is difficult because machine learning struggles with the…

The development of high-dimensional generative models has recently gained a great surge of interest with the introduction of variational auto-encoders and generative adversarial neural networks. Different variants have been proposed where…

Denoising diffusion probabilistic models are a promising new class of generative models that mark a milestone in high-quality image generation. This paper showcases their ability to sequentially generate video, surpassing prior methods in…

Accurately anticipating how complex, diverse scenes will evolve requires models that represent uncertainty, simulate along extended interaction chains, and efficiently explore many plausible futures. Yet most existing approaches rely on…

Simple as it seems, moving an object to another location within an image is, in fact, a challenging image-editing task that requires re-harmonizing the lighting, adjusting the pose based on perspective, accurately filling occluded regions,…

Generating long-duration videos has always been a significant challenge due to the inherent complexity of spatio-temporal domain and the substantial GPU memory demands required to calculate huge size tensors. While diffusion based…

Video anticipation is the task of predicting one/multiple future representation(s) given limited, partial observation. This is a challenging task due to the fact that given limited observation, the future representation can be highly…

We propose a deep video prediction model conditioned on a single image and an action class. To generate future frames, we first detect keypoints of a moving object and predict future motion as a sequence of keypoints. The input image is…

We present 3DScenePrompt, a framework that generates the next video chunk from arbitrary-length input while enabling precise camera control and preserving scene consistency. Unlike methods conditioned on a single image or a short clip, we…

Deep neural networks have become increasingly of interest in dynamical system prediction, but out-of-distribution generalization and long-term stability still remains challenging. In this work, we treat the domain parameters of dynamical…