相关论文: Distilling Governing Laws and Source Input for Dyn…
A video autoencoder is proposed for learning disentan- gled representations of 3D structure and camera pose from videos in a self-supervised manner. Relying on temporal continuity in videos, our work assumes that the 3D scene structure in…
We consider the problem of estimating an object's physical properties such as mass, friction, and elasticity directly from video sequences. Such a system identification problem is fundamentally ill-posed due to the loss of information…
A complete understanding of physical systems requires models that are accurate and obeys natural conservation laws. Recent trends in representation learning involve learning Lagrangian from data rather than the direct discovery of governing…
We introduce latent intuitive physics, a transfer learning framework for physics simulation that can infer hidden properties of fluids from a single 3D video and simulate the observed fluid in novel scenes. Our key insight is to use latent…
We introduce a data-driven method for learning the equations of motion of mechanical systems directly from position measurements, without requiring access to velocity data. This is particularly relevant in system identification tasks where…
Dynamical systems are typically governed by a set of linear/nonlinear differential equations. Distilling the analytical form of these equations from very limited data remains intractable in many disciplines such as physics, biology, climate…
Although deep-learning has been successfully applied in a variety of science and engineering problems owing to its strong high-dimensional nonlinear mapping capability, it is of limited use in scientific knowledge discovery. In this work,…
Identifying the governing equations of a nonlinear dynamical system is key to both understanding the physical features of the system and constructing an accurate model of the dynamics that generalizes well beyond the available data. We…
Videos provide a rich source of information, but it is generally hard to extract dynamical parameters of interest. Inferring those parameters from a video stream would be beneficial for physical reasoning. Robots performing tasks in dynamic…
Deep neural networks (DNN) have been used to model nonlinear relations between physical quantities. Those DNNs are embedded in physical systems described by partial differential equations (PDE) and trained by minimizing a loss function that…
Data-based discovery of effective, coarse-grained (CG) models of high-dimensional dynamical systems presents a unique challenge in computational physics and particularly in the context of multiscale problems. The present paper offers a…
We investigate the emergence of intuitive physics understanding in general-purpose deep neural network models trained to predict masked regions in natural videos. Leveraging the violation-of-expectation framework, we find that video…
Developing world models that understand complex physical interactions is essential for advancing robotic planning and simulation.However, existing methods often struggle to accurately model the environment under conditions of data scarcity…
This paper introduces an unsupervised framework to extract semantically rich features for video representation. Inspired by how the human visual system groups objects based on motion cues, we propose a deep convolutional neural network that…
Next-frame prediction is a useful and powerful method for modelling and understanding the dynamics of video data. Inspired by the empirical success of causal language modelling and next-token prediction in language modelling, we explore the…
Dynamic patterns are characterized by complex spatial and motion patterns. Understanding dynamic patterns requires a disentangled representational model that separates the factorial components. A commonly used model for dynamic patterns is…
Conventional video compression approaches use the predictive coding architecture and encode the corresponding motion information and residual information. In this paper, taking advantage of both classical architecture in the conventional…
In this work, we propose a unified framework, called Visual Reasoning with Differ-entiable Physics (VRDP), that can jointly learn visual concepts and infer physics models of objects and their interactions from videos and language. This is…
In this paper, we aim to jointly model the geometry, appearance, and physical information of 3D scenes solely from dynamic multi-view videos, without relying on any physical priors. Existing works typically employ physical losses merely as…
Conservation laws are an inherent feature in many systems modeling real world phenomena, in particular, those modeling biological and chemical systems. If the form of the underlying dynamical system is known, linear algebra and algebraic…