Article
Computer Science, Software Engineering
Levi Fussell, Kevin Bergamin, Daniel Holden
Summary: This paper demonstrates a method for motion tracking of physically simulated characters using supervised learning and optimizing the policy directly. By training a world model to approximate a specific subset of the environment's transition function, the policy can be optimized to minimize tracking error. Compared to popular model-free methods, this approach consistently achieves higher quality control in a shorter training time with reduced sensitivity to experience gathering rate, dataset size, and distribution.
ACM TRANSACTIONS ON GRAPHICS
(2021)
Article
Computer Science, Software Engineering
Lucas Mourot, Ludovic Hoyet, Francois Le Clerc, Francois Schnitzler, Pierre Hellier
Summary: This article provides a comprehensive survey on the state-of-the-art approaches in skeleton-based human character animation using deep learning and deep reinforcement learning. It covers motion data representations, common datasets, as well as methods to enhance deep models for learning spatial and temporal patterns in motion data. The latest methods are divided into motion synthesis, character control, and motion editing categories, with a discussion on limitations and future research directions.
COMPUTER GRAPHICS FORUM
(2022)
Article
Computer Science, Software Engineering
Saeed Ghorbani, Ylva Ferstl, Daniel Holden, Nikolaus F. Troje, Marc-Andre Carbonneau
Summary: We introduce ZeroEGGS, a neural network framework for generating speech-driven gestures with zero-shot style control based on examples. Our model uses a Variational framework to learn style embeddings, enabling easy style modification. Through a series of experiments, we demonstrate the flexibility and generalizability of our model to new speakers and styles, and show its superiority in naturalness of motion, appropriateness for speech, and style portrayal compared to previous techniques. We also release a high-quality dataset for further research.
COMPUTER GRAPHICS FORUM
(2023)
Article
Computer Science, Software Engineering
Hugo Bertiche, Meysam Madadi, Sergio Escalera
Summary: The study introduces a methodology for automatically obtaining Pose Space Deformation (PSD) basis for rigged garments through deep learning, achieving realistic results in an unsupervised manner. By formulating deep learning as an implicit PBS, the models can be trained in a comparable amount of time, overcoming some drawbacks of traditional approaches.
ACM TRANSACTIONS ON GRAPHICS
(2021)
Article
Computer Science, Software Engineering
Samuel Carensac, Nicolas Pronost, Saida Bouakaz
Summary: The use of particles-based simulations for fluid animations is a widely used method in both industry and research sectors. This paper explores various optimizations for a GPU implementation of a recent particle-based fluid simulation algorithm. The study reveals that some optimizations have limited effectiveness for specific hardware configurations and may even have a negative impact on performance. Additionally, the use of warm-start reduces computation time but introduces cyclic instability in the simulation.
Article
Computer Science, Software Engineering
He Chen, Hyojoon Park, Kutay Macit, Ladislav Kavan
Summary: The new method captures detailed human motion, outputs precise point coordinates with unique labels, and relies on 2D images only. It utilizes a special motion capture suit and neural networks to process images, making it easy to replicate and deploy. The method can accurately capture various human poses, including challenging motions like yoga and gymnastics.
ACM TRANSACTIONS ON GRAPHICS
(2021)
Article
Computer Science, Software Engineering
Jaepyung Hwang, Shin Ishii
Summary: In this study, a novel motion re-targeting framework is proposed to generate natural motions of target robot character models. The framework takes into account both kinematic constraints and physical plausibility, maintaining balance and similar motion to the given source motions. The framework utilizes a simple physics model to interpret and inherit the balancing property of the source motion, providing balance-preserving target motions applicable to full-body physics simulation or real robot control.
COMPUTER GRAPHICS FORUM
(2023)
Article
Computer Science, Software Engineering
Jungdam Won, Deepak Gopinath, Jessica Hodgins
Summary: This paper presents an algorithm for building physics-based controllers for physically simulated characters with multiple degrees of freedom. The controllers, learned using conditional VAEs, can generate diverse and plausible human motions without conditioning on specific goals. They are robust enough to solve complex downstream tasks efficiently.
ACM TRANSACTIONS ON GRAPHICS
(2022)
Article
Computer Science, Software Engineering
Kai Bai, Wei Li, Mathieu Desbrun, Xiaopei Liu
Summary: The article proposes a novel learning approach for dynamically upsampling smoke flows based on a training set of coarse and fine resolution flows. The network constructs a corresponding dictionary during training and is able to provide accurate upsampling through fast evaluation.
ACM TRANSACTIONS ON GRAPHICS
(2021)
Article
Computer Science, Software Engineering
Qiaodong Cui, Timothy Langlois, Pradeep Sen, Theodore Kim
Summary: In this paper, a fast and expressive method for simulating fluids over radial domains is introduced, which includes discs, spheres, cylinders, ellipses, spheroids, and tori. The method, referred to as spiral-spectral fluid simulations, generalizes the spectral approach of Laplacian Eigenfunctions and includes carefully selected enrichment functions to remove singularities and establish orthogonality at minimal cost. The method also supports viscosity analytically and includes basis functions designed to support scalable FFT-based reconstructions. Additionally, an efficient way of computing necessary advection tensors is presented, and the approach applies to both three-dimensional flows and their surface-based, codimensional variants, with completeness of basis representation established and comparison made against existing solvers.
ACM TRANSACTIONS ON GRAPHICS
(2021)
Article
Computer Science, Software Engineering
Matthias Mueller, Miles Macklin, Nuttapong Chentanez, Stefan Jeschke
Summary: Shape matching method is a popular approach for simulating deformable objects in interactive applications without the need for mesh, but it is difficult to calibrate and does not conserve volume.
COMPUTER GRAPHICS FORUM
(2022)
Article
Multidisciplinary Sciences
Jong-Hyun Kim, YoungBin Kim
Summary: This study proposes a neural network framework for modeling foam effects in liquid simulation without noise. By utilizing a denoising neural network, the problem of noise generated in the screen projection method is efficiently solved. Additionally, the foam particles are generated through the inverse transformation of 2D space into 3D space, solving the issue of small-sized foam dissipation in traditional denoising networks.
Article
Computer Science, Artificial Intelligence
Yujie Shi, Baoqing Wang
Summary: To enhance the naturalness and coordination of computer animation virtual idol characters, a virtual character interaction control method is proposed, together with an artificial neural network motion controller based on motion capture data. Experimental results demonstrate that this approach effectively prevents virtual characters from assuming undesirable motion postures.
NEURAL COMPUTING & APPLICATIONS
(2023)
Article
Computer Science, Software Engineering
Longwen Zhang, Chuxiao Zeng, Qixuan Zhang, Hongyang Lin, Ruixiang Cao, Wei Yang, Lan Xu, Jingyi Yu
Summary: This paper presents a new learning-based, video-driven approach for generating dynamic facial geometries with high-quality physically-based assets; modeling facial expressions, geometry, and physically-based textures using separate VAEs to preserve characteristics across respective attributes; comprehensive experiments show that this technique provides higher accuracy and visual fidelity in facial reconstruction and animation.
ACM TRANSACTIONS ON GRAPHICS
(2022)
Article
Computer Science, Software Engineering
Yeonjoon Kim, Sung-Hee Lee
Summary: In this paper, a novel keyframe-based framework is introduced to automatically generate multi-contact character motions. The system includes key-pose planning and interpolation components, which can synthesize plausible interaction motions and demonstrate scalability.
Article
Computer Science, Software Engineering
Morten Bojsen-Hansen, Chris Wojtan
ACM TRANSACTIONS ON GRAPHICS
(2016)
Article
Computer Science, Software Engineering
David Hahn, Chris Wojtan
ACM TRANSACTIONS ON GRAPHICS
(2016)
Article
Computer Science, Software Engineering
Fang Da, David Hahn, Christopher Batty, Chris Wojtan, Eitan Grinspun
ACM TRANSACTIONS ON GRAPHICS
(2016)
Article
Computer Science, Software Engineering
Ryan Goldade, Christopher Batty, Chris Wojtan
COMPUTER GRAPHICS FORUM
(2016)
Article
Computer Science, Software Engineering
P. -L. Manteaux, C. Wojtan, R. Narain, S. Redon, F. Faure, M. -P. Cani
COMPUTER GRAPHICS FORUM
(2017)
Article
Computer Science, Software Engineering
Florian Ferstl, Ryoichi Ando, Chris Wojtan, Ruediger Westermann, Nils Thuerey
COMPUTER GRAPHICS FORUM
(2016)
Article
Computer Science, Software Engineering
T. Sato, C. Wojtan, N. Thuerey, T. Igarashi, R. Ando
COMPUTER GRAPHICS FORUM
(2018)
Article
Computer Science, Software Engineering
Stefan Jeschke, Tomas Skrivan, Matthias Muller-Fischer, Nuttapong Chentanez, Miles Macklin, Chris Wojtan
ACM TRANSACTIONS ON GRAPHICS
(2018)
Article
Computer Science, Software Engineering
Camille Schreck, Christian Hafner, Chris Wojtan
ACM TRANSACTIONS ON GRAPHICS
(2019)
Article
Computer Science, Software Engineering
Georg Sperl, Rahul Narain, Chris Wojtan
ACM TRANSACTIONS ON GRAPHICS
(2020)
Article
Computer Science, Software Engineering
Sadashige Ishida, Peter Synak, Fumiya Narita, Toshiya Hachisuka, Chris Wojtan
ACM TRANSACTIONS ON GRAPHICS
(2020)
Article
Computer Science, Software Engineering
Tomas Skrivan, Andreas Soderstrom, John Johansson, Christoph Sprenger, Ken Museth, Chris Wojtan
ACM TRANSACTIONS ON GRAPHICS
(2020)
Article
Computer Science, Software Engineering
Camille Schreck, Chris Wojtan
COMPUTER GRAPHICS FORUM
(2020)
Article
Computer Science, Software Engineering
S. Jeschke, C. Hafner, N. Chentanez, M. Macklin, M. Mueller-Fischer, C. Wojtan
COMPUTER GRAPHICS FORUM
(2020)
Article
Computer Science, Software Engineering
Stefan Jeschke, Chris Wojtan
ACM TRANSACTIONS ON GRAPHICS
(2017)