Fig 1 - uploaded by Nadia Magnenat Thalmann
Content may be subject to copyright.
View of the trajectory of the least moving point over the sole during one foot step. In black is a wire frame view of the sole of the character, in red are the vertices selected during the step, and eventually the blue arrows shows the transitions between each point.
Source publication
Footskate is a common problem encountered in interactive applications dealing with virtual character animations. It has proven difficult to fix without the use of complex numerical methods, which require expert skills for their implementations, along with a fair amount of user interaction to correct a motion. On the other hand, deformable bodies ar...
Similar publications
Citations
... As a result, the generated motions often lead to mismatches between root trajectories and motion postures, which cause the foot sliding problem. Therefore, post-processing strategies based on physical constraint-based pose correction [9,10] and modification of root joint translations [11,12] are used to eliminate sliding. Essentially, post-processing is a secondary editing of the motion to obtain a matched consistency between the root trajectory and motion postures [13]. ...
... Although it can produce visually natural motion movements, it is challenging to entangle in the end-to-end optimized neural networks, and the process is tedious. Inspired by the post-processing algorithms [10][11][12], we believe that the solution for sliding lies in guaranteeing the matching between the root trajectory and motion postures. We do not attempt to forecast the root trajectory directly. ...
Keyframe‐based motion synthesis holds significant effects in games and movies. Existing methods for complex motion synthesis often require secondary post‐processing to eliminate foot sliding to yield satisfied motions. In this paper, we analyze the cause of the sliding issue attributed to the mismatch between root trajectory and motion postures. To address the problem, we propose a novel end‐to‐end Spatial‐Temporal transformer network conditioned on foot contact information for high‐quality keyframe‐based motion synthesis. Specifically, our model mainly compromises a spatial‐temporal transformer encoder and two decoders to learn motion sequence features and predict motion postures and foot contact states. A novel constrained embedding, which consists of keyframes and foot contact constraints, is incorporated into the model to facilitate network learning from diversified control knowledge. To generate matched root trajectory with motion postures, we design a differentiable root trajectory reconstruction algorithm to construct root trajectory based on the decoder outputs. Qualitative and quantitative experiments on the public LaFAN1, Dance, and Martial Arts datasets demonstrate the superiority of our method in generating high‐quality complex motions compared with state‐of‐the‐arts.
... For both scenarios, replacing erroneous motions or filling in sparse data, we employ a post-processing step that involves motion refinement for foot-skating and/or foot-plant violations [LMT07]. ...
Motion capture sequences may contain erroneous data, especially when the motion is complex or performers are interacting closely and occlusions are frequent. Common practice is to have specialists visually detect the abnormalities and fix them manually. In this paper, we present a method to automatically analyze and fix motion capture sequences by using self‐similarity analysis. The premise of this work is that human motion data has a high‐degree of self‐similarity. Therefore, given enough motion data, erroneous motions are distinct when compared to other motions. We utilize motion‐words that consist of short sequences of transformations of groups of joints around a given motion frame. We search for the K‐nearest neighbors (KNN) set of each word using dynamic time warping and use it to detect and fix erroneous motions automatically. We demonstrate the effectiveness of our method in various examples, and evaluate by comparing to alternative methods and to manual cleaning.
... One common error that needs to be considered in perceptual validity is the foot-skating effect. Foot skating refers to the error that occurs in animation whereby the feet slide or float on the ground [64] . Foot skating often occurs when the recorded motion data are applied to different subjects whose position no longer fits the motion of the limbs, which is not applicable to our study. ...
Motion estimation methods have been proposed via different approaches, such as silhouette based, model based and image based estimations. However, these methods are highly dependent on the quality of motion data for optimal classification accuracy. Further, because of the complexity of existing algorithms for motion estimation, there are difficulties in interpretation. Hence, the contribution of this work is to model simple human motions for the purpose of recognizing different activity behavior patterns for classification analysis. The model is made up of three body component integrations - Backbone (BB), Upper Body (UB) and Lower Body (LB) - to form a simple 2D human stick figure. Two case studies involving a publicly available video of walking, running and jumping motions as well as experimental captures of Yoga motions are studied. Video motions are simplified into time-step image snapshots, which are later translated into a numeric 2D coordinate system. Initially, the human pelvis is considered the origin of the stick figure. The stick model was drawn by integrating the BB, UB and LB components based on the 2D body joint coordinates. The motion estimation model applies the concept of polynomial fitting to the coordinates data. Computations on the polynomial fitting coefficient deviations at sequential time steps were performed to evaluate the estimation tolerance. A summation of the precedent time-step coordinates with the average deviation metric is used iteratively to estimate the joint coordinates of the stick figure in the subsequent time step to develop the entire motion model. Finally, the developed motion estimation mathematical model was compared to the actual motion phases for classification efficiencies using the Bayes, Lazy, Function, Meta, Misc, Rules and Trees classifiers. Our findings revealed the feasibility of using 2D stick-model matching estimation for human motion classification analysis.
... In such cases, aligning the dataset (multiple sequences) will result in loss of correlation within the different DOFs of each single sequence (except for the reference sequence). This problem will manifest itself as artifacts, one of which is commonly known as footskating [39]. In order to prevent this from happening, we compute the global similarity values between the sequences. ...
Human motion can be carried out with a variety of different affects or styles such as happy, sad, energetic, and tired among many others. Modeling and classifying these styles, and more importantly, translating them from one sequence onto another has become a popular problem in the fields of graphics, multimedia, and human computer interaction. In this paper, radial basis functions (RBF) are used to model and extract stylistic and affective features from motion data. We demonstrate that using only a few basis functions per degree of freedom, successful modeling of styles in cycles of human walk can be achieved. Furthermore, we employ an ensemble of RBF neural networks to learn the affective/stylistic features following time warping and principal component analysis. The system learns the components and classifies stylistic motion sequences into distinct affective and stylistic classes. The system also utilizes the ensemble of neural networks to learn motion affects and styles such that it can translate them onto neutral input sequences. Experimental results along with both numerical and perceptual validations confirm the highly accurate and effective performance of the system.
... A five steps kinematics algorithm to remove the foot skating was developed by [31]. We employ a skinbased approach to perform the same cleanup [33] while [18] used a fully IK based approach ...
In this paper we present the Virtual Try On (VTO), an online application that assists users in the evaluation of garments in an online shopping scenario. With the VTO users can create a size-correct virtual representation of themselves, allowing them to virtually try on physically simulated garments which can then be animated. We discuss the requirements of web based physically simulated clothes through a discussion of its building blocks: body sizing, motion retargeting and real-time physically based simulation of resizable and customizable garments. We also discuss its place in a CAD chain from 2D pattern data to the final production of actual garments.
... The general purpose collision removal corrects the penetrations due to the character's movements, for instance if the character puts its hand on its waist. The foot plant detection and enforcement can be done using one of the existing approaches [23, 24]. We picked the one from Lyard as it seems to be the easiest one to implement. ...
... We would also like to introduce physical deformations of the body in order to produce a more accurate adaptation and skin deformation. Eventually, we would like to implement the footskating removal method from [23] because the one from [24] sometimes introduced small artifacts in the final animations.Figure 1: Illustration of the issue related to the per-frame approaches for collision removal. ...
With the increasing performances of the graphics hardware, virtual reality applica- tions are reaching a new level of realism. It is now possible to animate entire crowds of virtual avatars, or to display in real-time highly realistic deformable characters. This new type of applications requires that characters are deformed, either to generate a large number of individuals for creating a crowd, or to match a particular shape. To make the animation fit to the animated character and to prevent self-collisions, adapting the motion is mandatory. Unlike previous approaches which relied on skeletal models, this paper presents a method considering the actual shape of the character's body to perform the adaptation. Our approach uses spacetime optimization to remove the self- penetration, and finally re-establishes the balance of the motion. We also introduce an interpolation scheme based on radial basis functions that can blend pre-calculated adaptations, and thus achieve real-time performances.
In this paper, we present a footplant detection method by adaptive determining foot height threshold. In our method, we firstly divide one step into a number of stages, each stage has different types of constraints. Then adaptively electing foot height threshold according to motion type and the length l of the minimum constraint frame that designed by the user and the maximum error φ of l to determine which foot should be planted. Finally, we verify the effectiveness of our approach from the path offset error.
Small variations in biological motion responsible for perception of characteristics, styles, or affects of the person performing the actions, are referred to as secondary features. This paper presents a novel method for separating and extracting spatiotemporal sets of secondary features from human motion data. The technique employs a dataset of sequences and identifies a corresponding neutral sequence through maximizing a similarity index based on correlation. Specific control points or temporal cues are then distributed through the input sequence. Distribution is carried out with the goal of maximizing an objective function successive to time warping. The optimized set of cues are used to reconstruct the neutral component of the signal using cubic splines. Accordingly, both spatial (movement and posture) and temporal secondary features are extracted from the stylistic input sequence. To illustrate one of the possible applications of the proposed technique, style translation is carried out. We illustrate that our proposed system can be used to extract various classes of secondary features from different actions such as walking, jumping, and running.
Virtual Try On (VTO) applications are still under development even if a few simplified applications start to be available.
A true VTO should let the user specify its measurements, so that a realistic avatar can be generated. Also, the avatar should
be animatable so that the worn cloth can be seen in motion. This later statement requires two technologies: motion adaptation
and real-time cloth simulation. Both have been extensively studied during the past decade, and state of the art techniques
may now enable the creation of a high quality VTO, allowing a user to virtually try on garments while shopping online. This
paper reviews the pieces that should be put together to build such an application.
