Related papers: Learning Vortex Dynamics for Fluid Inference and P…

Modeling the mechanics of fluid in complex scenes is vital to applications in design, graphics, and robotics. Learning-based methods provide fast and differentiable fluid simulators, however most prior work is unable to accurately model how…

Physics-informed deep learning has been developed as a novel paradigm for learning physical dynamics recently. While general physics-informed deep learning methods have shown early promise in learning fluid dynamics, they are difficult to…

Traditional fluid dynamics simulation pipelines combine numerical solvers with rendering, producing highly realistic results but at considerable computational cost. Diffusion-based generative video models offer a faster alternative, yet…

Real-life control tasks involve matters of various substances---rigid or soft bodies, liquid, gas---each with distinct physical behaviors. This poses challenges to traditional rigid-body physics engines. Particle-based simulators have been…

We present a novel deep learning architecture for probabilistic future prediction from video. We predict the future semantics, geometry and motion of complex real-world urban scenes and use this representation to control an autonomous…

A new variational inference method, SPH-ParVI, based on smoothed particle hydrodynamics (SPH), is proposed for sampling partially known densities (e.g. up to a constant) or sampling using gradients. SPH-ParVI simulates the flow of a fluid…

In this paper, we present a new model to simulate the formation, evolution, and break up of a thin film of fluid flowing over a curved surface. Referred to as the discrete droplet method (DDM), the model captures the evolution of thin fluid…

This paper proposes a method for performing continual learning of predictive models that facilitate the inference of future frames in video sequences. For a first given experience, an initial Variational Autoencoder, together with a set of…

We propose a self-supervised visual learning method by predicting the variable playback speeds of a video. Without semantic labels, we learn the spatio-temporal visual representation of the video by leveraging the variations in the visual…

This paper presents a novel physics-inspired deep learning approach for point cloud processing motivated by the natural flow phenomena in fluid mechanics. Our learning architecture jointly defines data in an Eulerian world space, using a…

Generative models that can model and predict sequences of future events can, in principle, learn to capture complex real-world phenomena, such as physical interactions. However, a central challenge in video prediction is that the future is…

Video diffusion models (VDMs) have advanced significantly in recent years, enabling the generation of highly realistic videos and drawing the attention of the community in their potential as world simulators. However, despite their…

Feature identification is an important task in many fluid dynamics applications and diverse methods have been developed for this purpose. These methods are based on a physical understanding of the underlying behavior of the flow in the…

Learned video compression methods have demonstrated great promise in catching up with traditional video codecs in their rate-distortion (R-D) performance. However, existing learned video compression schemes are limited by the binding of the…

Quantum solutions to differential equations represent quantum data -- states that contain relevant information about the system's behavior, yet are difficult to analyze. We propose a toolbox for reading out information from such data, where…

Video prediction is a fundamental task for various downstream applications, including robotics and world modeling. Although general video prediction models have achieved remarkable performance in standard scenarios, occlusion is still an…

Vortices are swirling regions of fluid that structure motion in gases and liquids across a wide range of scales, from laboratory-scale experiments to vast atmospheric currents. They play a key role in mixing, transport, and energy transfer,…

A dynamic scene has two types of elements: those that move fluidly and can be predicted from previous frames, and those which are disoccluded (exposed) and cannot be extrapolated. Prior approaches to video prediction typically learn either…

Learning interpretable representations of visual data is an important challenge, to make machines' decisions understandable to humans and to improve generalisation outside of the training distribution. To this end, we propose a deep…

Fast and stable fluid simulations are an essential prerequisite for applications ranging from computer-generated imagery to computer-aided design in research and development. However, solving the partial differential equations of…