Estimating contact dynamics

By Marcus A. Brubaker, Leonid Sigal, David J. Fleet. 2009

117 citations recorded by the source corpus.

Subfields: Biomedical Engineering, Computer Vision and Pattern Recognition, Control and Systems Engineering

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Biomedical Engineering

In Computer Vision and Pattern Recognition

In Control and Systems Engineering

Citations in the corpus

Visual Interaction Networks: Learning a Physics Simulator from Video (2017, background): “Several efforts [4, 6, 26, 27] have fit the parameters of Newtonian mechanics equations to systems depicted in images and videos, though the dynamic equations themselves were not learned.”
Unsupervised Learning for Physical Interaction through Video Prediction (2016, background): “Learning physics: Several works have explicitly addressed prediction of physical interactions, including predicting ball motion [5], block falling [2], the effects of forces [19, 18], future human interactions [9], and future car trajectories [26].”
Learning Visual Predictive Models of Physics for Playing Billiards (2015, methodology): “Learning Physics from Images and Videos Works of Wu et al. (2015); Bhat et al. (2002); Brubaker et al. (2009); Mottaghi et al. (2015) propose methods for estimating the parameters of Newtonian equations from images and videos.”
"What Happens If..." Learning to Predict the Effect of Forces in Images (2016, background): “[3] estimates forces applied to a human using the dynamics of contacts with different surfaces.”
Newtonian Image Understanding: Unfolding the Dynamics of Objects in Static Images (2015, neutral): “Physic-based human motion modeling was studied by [8, 6, 7, 32].”
Inverse Dynamics for Action Recognition (2013, background): “the foot ground contact with a damped linear spring modulated by two sigmoidal functions [22] (see Fig.”
Recognizing Human-Object Interactions in Still Images by Modeling the Mutual Context of Objects and Human Poses (2012, unknown): “Meanwhile , human poses have also been treated as context for many tasks such as motion capture [40] and inferring surface contact (such as joint torques and gravity) [41].”
PIP: Physical Interaction Prediction via Mental Imagery with Span Selection (2021, background): “These models can range from physics-based prediction models using pixel-level convolutional networks [31, 32, 33, 34, 29, 35] and scene-based learning [14, 36, 37, 38] to learning of physical representations of the intuitive physics [6, 2, 39] behind the interactions to make accurate prediction of…”
Generating Liquid Simulations with Deformation-aware Neural Networks (2017, background): “Early examples targeted minimization problems to determine physical trajectories or contact forces [4, 7], or plausible physics for interacting objects [21, 22].”
HuMoR: 3D Human Motion Model for Robust Pose Estimation (2021, background): “Models based on physics can potentially generalize more accurately [79, 53, 85, 78, 15, 14, 107], while also estimating global pose and environmental interactions.”
Discovery of complex behaviors through contact-invariant optimization (2012, background): “[Brubaker et al. 2009; Todorov 2011] reformulate contact as a smooth, rather than discontinuous phenomenon, where contact forces are always active, but smoothly diminish with the distance to the ground.”
Dark, Beyond Deep: A Paradigm Shift to Cognitive AI with Humanlike Common Sense (2020, background): “g.35d. Physics-based reasoning can not only be applied to scene understanding tasks, as above, but have also been applied to pose and hand recognition and analysis tasks. For example, Brubaker et al. [234,235,236] estimated the force of contacts and the torques of internal joints of human actions us”