Motion graphs++

By Jianyuan Min, Jinxiang Chai. ACM Transactions on Graphics, 2012

850 citations recorded by the source corpus.

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

View Paper: https://www.semanticscholar.org/paper/e3d631f0998e71db31a0740711ad03b19593590f

How researchers see this paper

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

In Computer Vision and Pattern Recognition

In Control and Systems Engineering

Citations in the corpus

Bailando: 3D Dance Generation by Actor-Critic GPT with Choreographic Memory (2022, background): “They are developed on the idea of “cropping and pasting”, which cut motion clips from existing data as individual nodes and splice these nodes to synthesize new motions according to proper rules [24, 4, 23, 26].”
On Human Motion Prediction Using Recurrent Neural Networks (2017, background): “wide variety of fields, such as action prediction for sociallyaware robotics [21], 3D people tracking within computer vision [13,43], motion generation for computer graphics [22] or modeling biological motion in psychology [42].”
Human Motion Diffusion as a Generative Prior (2023, background): “Motion Graphs [Kovar et al. 2008] can synthesize long motions via traversing discrete poses given a data corpus.”
HuMoR: 3D Human Motion Model for Robust Pose Estimation (2021, background): “imation [12, 48, 79, 50, 54, 37, 86] including recent recurrent and autoregressive models [32, 28, 35, 101, 52].”
Seeing Invisible Poses: Estimating 3D Body Pose from Egocentric Video (2016, methodology): “This graph is reminiscent of motion-graphs used for motion synthesis in computer graphics [25, 3].”
PiGraphs (2016, methodology): “Much prior work has addressed modeling of human motion style to allow for highlevel control and adaptation of motion data [Grochow et al. 2004; Shapiro 2011; Min and Chai 2012].”
Two Distributed-State Models For Generating High-Dimensional Time Series (2011, background): “Perhaps the simplest way to generate new motion sequences based on data is to sensibly concatenate short examples from a motion database to meet sparse user-specified constraints (Tanco and Hilton, 2000; Arikan and Forsyth, 2002; Kovar et al., 2002; Lee et al., 2002; Arikan et al., 2003).”
AI Choreographer: Music Conditioned 3D Dance Generation with AIST++ (2021, background): “Motion graphs [53, 7, 47] address this problem by generating motions in a non-parametric manner.”
Action-Reaction: Forecasting the Dynamics of Human Interaction (2014, methodology): “It should be noted that all of the interactive control approaches focus on synthesizing animations in response to a clearly deﬁned mapping [11,15] from the user input to pose.”
Robust motion in-betweening (2020, methodology): “Other statistical models, such as Gaussian Processes [Min and Chai 2012] and Gaussian Process Latent Variable Models [Grochow et al. 2004; Levine et al. 2012; Wang et al. 2008; Ye and Liu 2010] have been applied to the constrained motion control task, but are often limited by heavy run-time…”
Neural state machine for character-scene interactions (2019, background): “…et al. 2003], rapidly exploring random trees [Choi et al. 2011], A* search [Safonova and Hodgins 2007] reinforcement learning [Lo et al. 2012; Lo and Zwicker 2008] and Maximum A Posteriori (MAP) estimation [Min and Chai 2012], local optimization [Mordatch et al. 2012] and stochastic optimization.”
Character controllers using motion VAEs (2020, methodology): “Motion graphs [Kovar et al. 2002] were an early method of explicitly inferring the connectivity between arbitrary frames on motion clips, based on a pose distance metric being less than a given threshold.”