Davis Rempe, L. Guibas, Aaron Hertzmann, Bryan C. Russell, Ruben Villegas, Jimei Yang
{"title":"Contact and Human Dynamics from Monocular Video","authors":"Davis Rempe, L. Guibas, Aaron Hertzmann, Bryan C. Russell, Ruben Villegas, Jimei Yang","doi":"10.2312/sca.20201218","DOIUrl":"https://doi.org/10.2312/sca.20201218","url":null,"abstract":"Existing deep models predict 2D and 3D kinematic poses from video that are approximately accurate, but contain visible errors that violate physical constraints, such as feet penetrating the ground and bodies leaning at extreme angles. In this paper, we present a physics-based method for inferring 3D human motion from video sequences that takes initial 2D and 3D pose estimates as input. We first estimate ground contact timings with a novel prediction network which is trained without hand-labeled data. A physics-based trajectory optimization then solves for a physically-plausible motion, based on the inputs. We show this process produces motions that are significantly more realistic than those from purely kinematic methods, substantially improving quantitative measures of both kinematic and dynamic plausibility. We demonstrate our method on character animation and pose estimation tasks on dynamic motions of dancing and sports with complex contact patterns.","PeriodicalId":90147,"journal":{"name":"Computer animation. ACM SIGGRAPH Symposium on Computer Animation","volume":"56 1","pages":"71-87"},"PeriodicalIF":0.0,"publicationDate":"2020-07-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"76473018","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}
Jonathan Panuelos, Ryan Goldade, Christopher Batty
{"title":"Efficient Unified Stokes using a Polynomial Reduced Fluid Model","authors":"Jonathan Panuelos, Ryan Goldade, Christopher Batty","doi":"10.2312/sca.20201214","DOIUrl":"https://doi.org/10.2312/sca.20201214","url":null,"abstract":"","PeriodicalId":90147,"journal":{"name":"Computer animation. ACM SIGGRAPH Symposium on Computer Animation","volume":"103 1","pages":"1-3"},"PeriodicalIF":0.0,"publicationDate":"2020-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"83511616","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}
D. Chapman, Tim Daoust, Andras Ormos, Joseph Lewis
{"title":"WeightShift: Accelerating Animation at Framestore with Physics","authors":"D. Chapman, Tim Daoust, Andras Ormos, Joseph Lewis","doi":"10.2312/sca.20201219","DOIUrl":"https://doi.org/10.2312/sca.20201219","url":null,"abstract":"","PeriodicalId":90147,"journal":{"name":"Computer animation. ACM SIGGRAPH Symposium on Computer Animation","volume":"6 1","pages":"7-8"},"PeriodicalIF":0.0,"publicationDate":"2020-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"75858051","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}
Vojtech Krs, Torsten Hädrich, D. Michels, O. Deussen, S. Pirk, Bedrich Benes
{"title":"Wind Erosion: Shape Modifications by Interactive Particle-based Erosion and Deposition","authors":"Vojtech Krs, Torsten Hädrich, D. Michels, O. Deussen, S. Pirk, Bedrich Benes","doi":"10.2312/sca.20201216","DOIUrl":"https://doi.org/10.2312/sca.20201216","url":null,"abstract":"We present a novel user-assisted method for physics-inspired modeling of geomorphological features on polygonal meshes using material erosion and deposition as the driving mechanisms. Polygonal meshes defining an input scene are converted into a volumetric data structure that efficiently tracks the mass and boundary of the resulting morphological changes. We use Smoothed Particle Hydrodynamics to simulate fluids and to track eroded material. Eroded material is converted to material particles and naturally deposits in locations such as sinks and corners. Once deposited, we convert material particles back into the volumetric representation. CCS Concepts • Computing methodologies → Shape modeling;","PeriodicalId":90147,"journal":{"name":"Computer animation. ACM SIGGRAPH Symposium on Computer Animation","volume":"34 1","pages":"9-11"},"PeriodicalIF":0.0,"publicationDate":"2020-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"88175094","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}
Torsten Hädrich, J. Scheffczyk, Wojciech Palubicki, S. Pirk, D. Michels
{"title":"Interactive Wood Fracture","authors":"Torsten Hädrich, J. Scheffczyk, Wojciech Palubicki, S. Pirk, D. Michels","doi":"10.2312/sca.20201215","DOIUrl":"https://doi.org/10.2312/sca.20201215","url":null,"abstract":"We propose a new approach for the simulation of wood as anisotropic material that takes its inherent fiber structure into account. Our approach is based on the Position-based Dynamics framework. We use the Shape Matching approach as the basis for modeling the isotropic attribute of wood. For simulating anisotropic behavior we employ a fiber model based on the Cosserat rod theory. Our approach supports dynamic fracturing and captures typical breaking patterns of wood. CCS Concepts • Computing methodologies → Interactive simulation; Physical simulation;","PeriodicalId":90147,"journal":{"name":"Computer animation. ACM SIGGRAPH Symposium on Computer Animation","volume":"20 1","pages":"5-7"},"PeriodicalIF":0.0,"publicationDate":"2020-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"81584414","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}
{"title":"Fast Eulerian Fluid Simulation In Games Using Poisson Filters","authors":"A. Rabbani, Soufiane Khiat","doi":"10.2312/sca.20201221","DOIUrl":"https://doi.org/10.2312/sca.20201221","url":null,"abstract":"We present separable Poisson filters to accelerate the projection step in Eulerian fluid simulation. These filters are analytically computed offline and are easy to integrate into any fluid algorithm with a Poisson pressure computation step. We take advantage of the recursive structure of the Jacobi method to construct and then reduce a kernel that is used to solve the Poisson pressure entirely on GPU. Our method demonstrates promising speedups that scale well with both the grid resolution and the target Jacobi iteration. CCS Concepts • Computing methodologies → Physical simulation;","PeriodicalId":90147,"journal":{"name":"Computer animation. ACM SIGGRAPH Symposium on Computer Animation","volume":"3 1","pages":"11-13"},"PeriodicalIF":0.0,"publicationDate":"2020-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"87336514","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}
Rachida Ihya, A. Namir, S. E. Filali, Mohammed Ait Daoud, Fatima Zahra Guerss
{"title":"J48 algorithms of machine learning for predicting user's the acceptance of an E-orientation systems","authors":"Rachida Ihya, A. Namir, S. E. Filali, Mohammed Ait Daoud, Fatima Zahra Guerss","doi":"10.1145/3368756.3368995","DOIUrl":"https://doi.org/10.1145/3368756.3368995","url":null,"abstract":"Our research work is focused on educational guidance. For that, we propose to develop a model of E-orientation systems to understand the behavior of students towards E-orientation platforms. We rely on the Technology Acceptance Model (TAM) to position a shared qualitative questionnaire. Subsequently, we apply different Machine Learning classification algorithms to predict an acceptance model of E-orientation systems. In our study we worked with four algorithms: NaiveBayes, J48, LMT and SimpleLogistic. The simulation results that the highest classification accuracy performance is for the J48.","PeriodicalId":90147,"journal":{"name":"Computer animation. ACM SIGGRAPH Symposium on Computer Animation","volume":"57 1","pages":"20:1-20:8"},"PeriodicalIF":0.0,"publicationDate":"2019-10-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"84586882","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}
{"title":"SMART COMPANIES: How to reach sustainability during a digital transformation","authors":"Wail El Hilali, A. E. Manouar","doi":"10.1145/3286606.3286812","DOIUrl":"https://doi.org/10.1145/3286606.3286812","url":null,"abstract":"These are difficult times! Almost every industry is facing a real risk of disruption from cutting-edge technologies in the digital world. This reality drives companies to change and adapt their business models to remain competitive. They must succeed in transforming their business through technology, or they'll face destruction at the hands of their rivals that do. Furthermore, the search for sustainability continues to be one of the main matters that companies are investing in. This paper is an attempt to discuss how to seize the opportunity of digital transformations in order to reach sustainability. It starts by defining the concepts of digital transformation and sustainability. After, it answers, through real world examples, how companies, during a digital transformation, could increase profitability and their social footprint while reducing their impacts on environment. The paper discuss after, a survey, in the Moroccan context, of the relationship between digital transformation and sustainability among 15 companies (from 40 companies contacted) from different sectors. It also explains the Moroccan actual context using a game theory approach.","PeriodicalId":90147,"journal":{"name":"Computer animation. ACM SIGGRAPH Symposium on Computer Animation","volume":"96 1","pages":"35:1-35:6"},"PeriodicalIF":0.0,"publicationDate":"2018-10-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"72846337","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}
N. Cheema, S. Hosseini, J. Sprenger, E. Herrmann, H. Du, K. Fischer, P. Slusallek
{"title":"Dilated Temporal Fully-Convolutional Network for Semantic Segmentation of Motion Capture Data","authors":"N. Cheema, S. Hosseini, J. Sprenger, E. Herrmann, H. Du, K. Fischer, P. Slusallek","doi":"10.2312/sca.20181185","DOIUrl":"https://doi.org/10.2312/sca.20181185","url":null,"abstract":"Semantic segmentation of motion capture sequences plays a key part in many data-driven motion synthesis frameworks. It is a preprocessing step in which long recordings of motion capture sequences are partitioned into smaller segments. Afterwards, additional methods like statistical modeling can be applied to each group of structurally-similar segments to learn an abstract motion manifold. The segmentation task however often remains a manual task, which increases the effort and cost of generating large-scale motion databases. We therefore propose an automatic framework for semantic segmentation of motion capture data using a dilated temporal fully-convolutional network. Our model outperforms a state-of-the-art model in action segmentation, as well as three networks for sequence modeling. We further show our model is robust against high noisy training labels.","PeriodicalId":90147,"journal":{"name":"Computer animation. ACM SIGGRAPH Symposium on Computer Animation","volume":"20 1","pages":"5-6"},"PeriodicalIF":0.0,"publicationDate":"2018-06-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"87314673","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}