Proceedings of the 12th ACM SIGGRAPH Conference on Motion, Interaction and Games最新文献_第5页

3D Car Shape Reconstruction from a Single Sketch Image 3D汽车形状重建从一个单一的草图图像

Proceedings of the 12th ACM SIGGRAPH Conference on Motion, Interaction and Games Pub Date : 2019-10-28 DOI: 10.1145/3359566.3364693

N. Nozawa, Hubert P. H. Shum, Edmond S. L. Ho, S. Morishima

{"title":"3D Car Shape Reconstruction from a Single Sketch Image","authors":"N. Nozawa, Hubert P. H. Shum, Edmond S. L. Ho, S. Morishima","doi":"10.1145/3359566.3364693","DOIUrl":"https://doi.org/10.1145/3359566.3364693","url":null,"abstract":"Efficient car shape design is a challenging problem in both the automotive industry and the computer animation/games industry. In this paper, we present a system to reconstruct the 3D car shape from a single 2D sketch image. To learn the correlation between 2D sketches and 3D cars, we propose a Variational Autoencoder deep neural network that takes a 2D sketch and generates a set of multi-view depth & mask images, which are more effective representation comparing to 3D mesh, and can be combined to form the 3D car shape. To ensure the volume and diversity of the training data, we propose a feature-preserving car mesh augmentation pipeline for data augmentation. Since deep learning has limited capacity to reconstruct fine-detail features, we propose a lazy learning approach that constructs a small subspace based on a few relevant car samples in the database. Due to the small size of such a subspace, fine details can be represented effectively with a small number of parameters. With a low-cost optimization process, a high-quality car with detailed features is created. Experimental results show that the system performs consistently to create highly realistic cars of substantially different shape and topology, with a very low computational cost.","PeriodicalId":217888,"journal":{"name":"Proceedings of the 12th ACM SIGGRAPH Conference on Motion, Interaction and Games","volume":"34 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-10-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114279030","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 1

High fidelity simulation of corotational linear FEM for incompressible materials 不可压缩材料的同向线性有限元高保真模拟

Proceedings of the 12th ACM SIGGRAPH Conference on Motion, Interaction and Games Pub Date : 2019-10-28 DOI: 10.1145/3359566.3360079

Mihai Frâncu, Á. Ásgeirsson, Kenny Erleben

引用次数: 2

Global Momentum Preservation for Position-based Dynamics 基于位置动力学的全局动量保持

Proceedings of the 12th ACM SIGGRAPH Conference on Motion, Interaction and Games Pub Date : 2019-10-28 DOI: 10.1145/3359566.3360078

A. Dahl, Adam W. Bargteil

引用次数: 2

Contact Preserving Shape Transfer For Rigging-Free Motion Retargeting 无索具运动重定向的保接触形状转移

Proceedings of the 12th ACM SIGGRAPH Conference on Motion, Interaction and Games Pub Date : 2019-10-28 DOI: 10.1145/3359566.3360075

J. Basset, S. Wuhrer, Edmond Boyer, F. Multon

{"title":"Contact Preserving Shape Transfer For Rigging-Free Motion Retargeting","authors":"J. Basset, S. Wuhrer, Edmond Boyer, F. Multon","doi":"10.1145/3359566.3360075","DOIUrl":"https://doi.org/10.1145/3359566.3360075","url":null,"abstract":"Retargeting a motion from a source to a target character is an important problem in computer animation, as it allows to reuse existing rigged databases or transfer motion capture to virtual characters. Surface based pose transfer is a promising approach to avoid the trial-and-error process when controlling the joint angles. The main contribution of this paper is to investigate whether shape transfer instead of pose transfer would better preserve the original contextual meaning of the source pose. To this end, we propose an optimization-based method to deform the source shape+pose using three main energy functions: similarity to the target shape, body part volume preservation, and collision management (preserve existing contacts and prevent penetrations). The results show that our method is able to retarget complex poses, including several contacts, to very different morphologies. In particular, we introduce new contacts that are linked to the change in morphology, and which would be difficult to obtain with previous works based on pose transfer that aim at distance preservation between body parts. These preliminary results are encouraging and open several perspectives, such as decreasing computation time, and better understanding how to model pose and shape constraints.","PeriodicalId":217888,"journal":{"name":"Proceedings of the 12th ACM SIGGRAPH Conference on Motion, Interaction and Games","volume":"23 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-10-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128726160","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 9

A Robust Interactive Facial Animation Editing System 一个鲁棒的交互式面部动画编辑系统

Proceedings of the 12th ACM SIGGRAPH Conference on Motion, Interaction and Games Pub Date : 2019-10-28 DOI: 10.1145/3359566.3360076

Eloïse Berson, Catherine Soladié, Vincent Barrielle, Nicolas Stoiber

{"title":"A Robust Interactive Facial Animation Editing System","authors":"Eloïse Berson, Catherine Soladié, Vincent Barrielle, Nicolas Stoiber","doi":"10.1145/3359566.3360076","DOIUrl":"https://doi.org/10.1145/3359566.3360076","url":null,"abstract":"Over the past few years, the automatic generation of facial animation for virtual characters has garnered interest among the animation research and industry communities. Recent research contributions leverage machine-learning approaches to enable impressive capabilities at generating plausible facial animation from audio and/or video signals. However, these approaches do not address the problem of animation edition, meaning the need for correcting an unsatisfactory baseline animation or modifying the animation content itself. In facial animation pipelines, the process of editing an existing animation is just as important and time-consuming as producing a baseline. In this work, we propose a new learning-based approach to easily edit a facial animation from a set of intuitive control parameters. To cope with high-frequency components in facial movements and preserve a temporal coherency in the animation, we use a resolution-preserving fully convolutional neural network that maps control parameters to blendshapes coefficients sequences. We stack an additional resolution-preserving animation autoencoder after the regressor to ensure that the system outputs natural-looking animation. The proposed system is robust and can handle coarse, exaggerated edits from non-specialist users. It also retains the high-frequency motion of the facial animation. The training and the tests are performed on an extension of the B3D(AC)23032 database [Fanelli et al. 2010], that we make available with this paper at http://www.rennes.centralesupelec.fr/biwi3D.","PeriodicalId":217888,"journal":{"name":"Proceedings of the 12th ACM SIGGRAPH Conference on Motion, Interaction and Games","volume":"28 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-10-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121510752","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 5

Animation Synthesis Triggered by Vocal Mimics 由声音模仿触发的动画合成

Proceedings of the 12th ACM SIGGRAPH Conference on Motion, Interaction and Games Pub Date : 2019-10-18 DOI: 10.1145/3359566.3360067

A. Nivaggioli, D. Rohmer

引用次数: 1

Scenario Generalization of Data-driven Imitation Models in Crowd Simulation 人群仿真中数据驱动模仿模型的场景概化

Proceedings of the 12th ACM SIGGRAPH Conference on Motion, Interaction and Games Pub Date : 2019-10-02 DOI: 10.1145/3359566.3360087

Gang Qiao, H. Zhou, M. Kapadia, Sejong Yoon, V. Pavlovic

{"title":"Scenario Generalization of Data-driven Imitation Models in Crowd Simulation","authors":"Gang Qiao, H. Zhou, M. Kapadia, Sejong Yoon, V. Pavlovic","doi":"10.1145/3359566.3360087","DOIUrl":"https://doi.org/10.1145/3359566.3360087","url":null,"abstract":"Crowd simulation, the study of the movement of multiple agents in complex environments, presents a unique application domain for machine learning. One challenge in crowd simulation is to imitate the movement of expert agents in highly dense crowds. An imitation model could substitute an expert agent if the model behaves as good as the expert. This will bring many exciting applications. However, we believe no prior studies have considered the critical question of how training data and training methods affect imitators when these models are applied to novel scenarios. In this work, a general imitation model is represented by applying either the Behavior Cloning (BC) training method or a more sophisticated Generative Adversarial Imitation Learning (GAIL) method, on three typical types of data domains: standard benchmarks for evaluating crowd models, random sampling of state-action pairs, and egocentric scenarios that capture local interactions. Simulated results suggest that (i) simpler training methods are overall better than more complex training methods, (ii) training samples with diverse agent-agent and agent-obstacle interactions are beneficial for reducing collisions when the trained models are applied to new scenarios. We additionally evaluated our models in their ability to imitate real world crowd trajectories observed from surveillance videos. Our findings indicate that models trained on representative scenarios generalize to new, unseen situations observed in real human crowds.","PeriodicalId":217888,"journal":{"name":"Proceedings of the 12th ACM SIGGRAPH Conference on Motion, Interaction and Games","volume":"78 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-10-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127114051","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 4

Self-Imitation Learning of Locomotion Movements through Termination Curriculum 通过终止课程进行运动动作的自我模仿学习

Proceedings of the 12th ACM SIGGRAPH Conference on Motion, Interaction and Games Pub Date : 2019-07-27 DOI: 10.1145/3359566.3360072

Amin Babadi, Kourosh Naderi, Perttu Hämäläinen

{"title":"Self-Imitation Learning of Locomotion Movements through Termination Curriculum","authors":"Amin Babadi, Kourosh Naderi, Perttu Hämäläinen","doi":"10.1145/3359566.3360072","DOIUrl":"https://doi.org/10.1145/3359566.3360072","url":null,"abstract":"Animation and machine learning research have shown great advancements in the past decade, leading to robust and powerful methods for learning complex physically-based animations. However, learning can take hours or days, especially if no reference movement data is available. In this paper, we propose and evaluate a novel combination of techniques for accelerating the learning of stable locomotion movements through self-imitation learning of synthetic animations. First, we produce synthetic and cyclic reference movement using a recent online tree search approach that can discover stable walking gaits in a few minutes. This allows us to use reinforcement learning with Reference State Initialization (RSI) to find a neural network controller for imitating the synthesized reference motion. We further accelerate the learning using a novel curriculum learning approach called Termination Curriculum (TC), that adapts the episode termination threshold over time. The combination of the RSI and TC ensures that simulation budget is not wasted in regions of the state space not visited by the final policy. As a result, our agents can learn locomotion skills in just a few hours on a modest 4-core computer. We demonstrate this by producing locomotion movements for a variety of characters.","PeriodicalId":217888,"journal":{"name":"Proceedings of the 12th ACM SIGGRAPH Conference on Motion, Interaction and Games","volume":"50 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-07-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127332864","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 7