相关论文: PhysVideoGenerator: Towards Physically Aware Video…

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…

In this paper, we investigate the challenge of spatio-temporal video prediction task, which involves generating future video frames based on historical spatio-temporal observation streams. Existing approaches typically utilize external…

Can we learn the physics of matter in motion directly from images and video--and trust it? Answering this question requires integrating experiments, physics-based simulation, and data across traditionally separate disciplines. Much of this…

World models compress rich sensory streams into compact latent codes that anticipate future observations. We let separate agents acquire such models from distinct viewpoints of the same environment without any parameter sharing or…

Recent unsupervised pre-training methods have shown to be effective on language and vision domains by learning useful representations for multiple downstream tasks. In this paper, we investigate if such unsupervised pre-training methods can…

Based on life-long observations of physical, chemical, and biologic phenomena in the natural world, humans can often easily picture in their minds what an object will look like in the future. But, what about computers? In this paper, we…

This work aims to learn a high-quality text-to-video (T2V) generative model by leveraging a pre-trained text-to-image (T2I) model as a basis. It is a highly desirable yet challenging task to simultaneously a) accomplish the synthesis of…

Video compositing combines live-action footage to create video production, serving as a crucial technique in video creation and film production. Traditional pipelines require intensive labor efforts and expert collaboration, resulting in…

We introduce VL-JEPA, a vision-language model built on a Joint Embedding Predictive Architecture (JEPA). Instead of autoregressively generating tokens as in classical VLMs, VL-JEPA predicts continuous embeddings of the target texts. By…

Autoregressive transformers have shown remarkable success in video generation. However, the transformers are prohibited from directly learning the long-term dependency in videos due to the quadratic complexity of self-attention, and…

While language models have become impactful in many real-world applications, video generation remains largely confined to entertainment. Motivated by video's inherent capacity to demonstrate physical-world information that is difficult to…

Recently, diffusion models like StableDiffusion have achieved impressive image generation results. However, the generation process of such diffusion models is uncontrollable, which makes it hard to generate videos with continuous and…

Expressive text-to-speech systems have undergone significant advancements owing to prosody modeling, but conventional methods can still be improved. Traditional approaches have relied on the autoregressive method to predict the quantized…

Do video diffusion models encode signals predictive of physical plausibility? We probe intermediate denoising representations of a pretrained Diffusion Transformer (DiT) and find that physically plausible and implausible videos are…

The recent success in StyleGAN demonstrates that pre-trained StyleGAN latent space is useful for realistic video generation. However, the generated motion in the video is usually not semantically meaningful due to the difficulty of…

Variational autoencoders allow to learn a lower-dimensional latent space based on high-dimensional input/output data. Using video clips as input data, the encoder may be used to describe the movement of an object in the video without ground…

Large-scale video generative models are trained on vast and diverse visual data, enabling them to internalize rich structural, semantic, and dynamic priors of the visual world. While these models have demonstrated impressive generative…

We propose a new class of physics-informed neural networks, called Physics-Informed Generator-Encoder Adversarial Networks, to effectively address the challenges posed by forward, inverse, and mixed problems in stochastic differential…

While text-to-video diffusion models have made significant strides, many still face challenges in generating videos with temporal consistency. Within diffusion frameworks, guidance techniques have proven effective in enhancing output…

Physics-integrated generative modeling is a class of hybrid or grey-box modeling in which we augment the the data-driven model with the physics knowledge governing the data distribution. The use of physics knowledge allows the generative…