Learning‐based pose edition for efficient and interactive design

Victor, Léon; Meyer, Alexandre; Bouakaz, Saïda

doi:10.1002/cav.2013

Cited by 2 publications

(2 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Recently, Victor et al [2021] introduce an IK solver that is based on an autoencoder structure, which aligns hand joints to the target position from a starting pose. However, their model has some limitations as it modifies the entire skeleton each time an end-effector is altered, resulting in the emergence of foot-sliding artifacts and a lack of temporal coherence.…”

Section: Learned Inverse Kinematicsmentioning

confidence: 99%

SparsePoser: Real-time Full-body Motion Reconstruction from Sparse Data

Ponton,

Yun,

Aristidou

et al. 2023

ACM Trans. Graph.

View full text Add to dashboard Cite

Accurate and reliable human motion reconstruction is crucial for creating natural interactions of full-body avatars in Virtual Reality (VR) and entertainment applications. As the Metaverse and social applications gain popularity, users are seeking cost-effective solutions to create full-body animations that are comparable in quality to those produced by commercial motion capture systems. In order to provide affordable solutions though, it is important to minimize the number of sensors attached to the subject’s body. Unfortunately, reconstructing the full-body pose from sparse data is a heavily under-determined problem. Some studies that use IMU sensors face challenges in reconstructing the pose due to positional drift and ambiguity of the poses. In recent years, some mainstream VR systems have released 6-degree-of-freedom (6-DoF) tracking devices providing positional and rotational information. Nevertheless, most solutions for reconstructing full-body poses rely on traditional inverse kinematics (IK) solutions, which often produce non-continuous and unnatural poses. In this paper, we introduce SparsePoser, a novel deep learning-based solution for reconstructing a full-body pose from a reduced set of six tracking devices. Our system incorporates a convolutional-based autoencoder that synthesizes high-quality continuous human poses by learning the human motion manifold from motion capture data. Then, we employ a learned IK component, made of multiple lightweight feed-forward neural networks, to adjust the hands and feet towards the corresponding trackers. We extensively evaluate our method on publicly available motion capture datasets and with real-time live demos. We show that our method outperforms state-of-the-art techniques using IMU sensors or 6-DoF tracking devices, and can be used for users with different body dimensions and proportions.

show abstract

Section: Learned Inverse Kinematicsmentioning

confidence: 99%

SparsePoser: Real-time Full-body Motion Reconstruction from Sparse Data

Ponton,

Yun,

Aristidou

et al. 2023

ACM Trans. Graph.

View full text Add to dashboard Cite

show abstract

“…Animation courses utilize both online and offline hybrid teaching methods to make full use of afterschool time and expand students' access to knowledge [15]. Léon Victor et al In computer-assisted keyframe animation, the designer defines the character's key poses by manipulating the character's underlying skeleton to make it vividly rendered according to the scripted content, which is used for the explanation of the character in the later stage of Motion Graphics (MG) [16]. Noetel, M. et al argued that testing the effect of multimedia art design on learning or cognitive load found that multimedia art enables students to learn professional techniques subtly and cultivates the awareness of students to be actively informed of the new concepts, techniques and methods in the industry positions, so as to achieve the purpose of improving their own professional and business level [17].…”

Section: Introductionmentioning

confidence: 99%

Analysis of the Teaching Path of Animation Film Majors Integrating Digital Visual Space in the Context of Digital Media Art

2023

Applied Mathematics and Nonlinear Sciences

View full text Add to dashboard Cite

In this study, we first adopt the dynamic stereo vision spatial coordinate measurement method of non-zoom cameras, establish a coordinate measurement model based on differential GPS, and study the application of the spatial coordinates of dynamic stereo digital vision systems in animation design. Secondly, the internal and external parameters of the camera are defined as the static error of the dynamic stereo vision system so as to provide an easy and quick-to-use design tool for the teaching of animation film majors. Finally, a test sequence animation sample set is used to verify the teaching effect of digital visual space based on animation design. The results show that in the multi-comparison test of animation quality against pixel bit rate, the animation design samples were found to have frame rates in the range of 5-30 Fps. And under the condition of having extra bandwidth, the animation feature learning evaluation dimension is 2589, and increasing the animation visual frame rate can improve the output picture quality of animation more effectively. It shows that the integration of digital visual space in the context of digital media art can allow students to have enough project sources for learning and practicing so as to improve their professional ability.

show abstract

Learning‐based pose edition for efficient and interactive design

Cited by 2 publications

References 17 publications

SparsePoser: Real-time Full-body Motion Reconstruction from Sparse Data

SparsePoser: Real-time Full-body Motion Reconstruction from Sparse Data

Analysis of the Teaching Path of Animation Film Majors Integrating Digital Visual Space in the Context of Digital Media Art

Contact Info

Product

Resources

About