检索结果-内蒙古大学图书馆

Conference on Motion, Interaction and Games (MIG)

作者： Klein, Alex Yumak, Zerrin Beij, Arjen van der Stappen, A. Frank Univ Utrecht Dept Informat & Comp Sci Utrecht Netherlands Guerilla Games Amsterdam Netherlands

ISBN: (纸本)9781450369947

We present a data-driven gaze animation method using recurrent neural networks. The neural network is trained with motion capture data including different poses such as standing, sitting, and lying down and is able to learn the constraints related with each particular pose. A simplified version of the neural network is also presented for Level of Detail (LOD) animation. We compare various neural network architectures and show that our method produces natural gaze motion in real-time. Results from a user study conducted among game industry professionals shows that our method has better perceived naturalness compared to the procedural gaze animation system of a well-known game company. Our approach is the first one to show the feasibility of gaze motions using deep neural networks.

关键词： gaze animation recurrent neural networks motion capture data-driven animation

来源：评论

学校读者我要写书评

暂无评论

Visualizing Life in the Deep: A Creative Pipeline for data-driven animations to Facilitate Marine Mammal Research, Outreach, and Conservation

Visualizing Life in the Deep: A Creative Pipeline for Data-D...

引用

IEEE Conference on VIS Arts Program (VISAP)

作者： Kendall-Bar, Jessica Kendall-Bar, Nicolas Forbes, Angus G. McDonald, Gitte Ponganis, Paul J. Williams, Cassondra Horning, Markus Hindle, Allyson Klinck, Holger Beltran, Roxanne S. Friedlaender, Ari S. Wiley, David Costa, Daniel P. Williams, Terrie M. UC Santa Cruz Ecol & Evolutionary Biol Santa Cruz CA 95064 USA Kendall Bar Studios Santa Cruz CA 95064 USA UC Santa Cruz Computat Media Santa Cruz CA USA San Jose State Univ Moss Landing Marine Labs San Jose CA 95192 USA Univ Calif San Diego Scripps Inst Oceanog San Diego CA USA Natl Marine Mammal Fdn San Diego CA USA Wildlife Technol Frontiers Seward AL USA Univ Nevada Sch Life Sci Las Vegas NV 89154 USA Cornell Univ Ctr Conservat Bioacoust Ithaca NY USA Oregon State Univ Marine Mammal Inst Corvallis OR 97331 USA UC Santa Cruz Inst Marine Sci Santa Cruz CA USA NOAA Stellwagen Bank Natl Marine Sanctuary Scituate MA USA

ISBN: (纸本)9781665440219

In this paper, we introduce a creative pipeline to incorporate physiological and behavioral data from contemporary marine mammal research into data-driven animations, leveraging functionality from industry tools and custom scripts to promote scientific insights, public awareness, and conservation outcomes. Our framework can flexibly transform data describing animals' orientation, position, heart rate, and swimming stroke rate to control the position, rotation, and behavior of 3D models, to render animations, and to drive data sonification. Additionally, we explore the challenges of unifying disparate datasets gathered by an interdisciplinary team of researchers, and outline our design process for creating meaningful data visualization tools and animations. As part of our pipeline, we clean and process raw acceleration and electrophysiological signals to expedite complex multi-stream data analysis and the identification of critical foraging and escape behaviors. We provide details about four animation projects illustrating marine mammal datasets. These animations, commissioned by scientists to achieve outreach and conservation outcomes, have successfully increased the reach and engagement of the scientific projects they describe. These impactful visualizations help scientists identify behavioral responses to disturbance, increase public awareness of human-caused disturbance, and help build momentum for targeted conservation efforts backed by scientific evidence.

关键词： data-driven animation marine mammals art-science research science communication ocean sciences

来源：评论

学校读者我要写书评

暂无评论

NPGA: Neural Parametric Gaussian Avatars 24

NPGA: Neural Parametric Gaussian Avatars

引用

2024 SIGGRAPH Asia Conference

作者： Giebenhain, Simon Kirschstein, Tobias Ruenz, Martin Agapito, Lourdes Niessner, Matthias Tech Univ Munich Munich Germany Synthesia Munich Germany UCL London England Synthesia London England

ISBN: (纸本)9798400711312

The creation of high-fidelity, digital versions of human heads is an important stepping stone in the process of further integrating virtual components into our everyday lives. Constructing such avatars is a challenging research problem, due to a high demand for photo-realism and real-time rendering performance. In this work, we propose Neural Parametric Gaussian Avatars (NPGA), a data-driven approach to create high-fidelity, controllable avatars from multi-view video recordings. We build our method around 3D Gaussian splatting for its highly efficient rendering and to inherit the topological flexibility of point clouds. In contrast to previous work, we condition our avatars' dynamics on the rich expression space of neural parametric head models (NPHM), instead of mesh-based 3DMMs. To this end, we distill the backward deformation field of our underlying NPHM into forward deformations which are compatible with rasterization-based rendering. All remaining fine-scale, expression-dependent details are learned from the multi-view videos. For increased representational capacity of our avatars, we propose per-Gaussian latent features that condition each primitives dynamic behavior. To regularize this increased dynamic expressivity, we propose Laplacian terms on the latent features and predicted dynamics. We evaluate our method on the public NeRSemble dataset, demonstrating that NPGA significantly outperforms the previous state-of-the-art avatars on the self-reenactment task by approximate to 2.6 PSNR. Furthermore, we demonstrate accurate animation capabilities from real-world monocular videos.

关键词： Virtual avatars 3D Gaussian splatting data-driven animation 3d morphable models

来源：评论

学校读者我要写书评

暂无评论

Learning Virtual Chimeras by Dynamic Motion Reassembly

引用

ACM TRANSACTIONS ON GRAPHICS 2022年第6期41卷 p1-13页

作者： Lee, Seyoung Lee, Jiye Lee, Jehee Seoul Natl Univ Dept Comp Sci & Engn Seoul South Korea NCsoft Kyungkido South Korea

The Chimera is a mythological hybrid creature composed of different animal parts. The chimera's movements are highly dependent on the spatial and temporal alignments of its composing parts. In this paper, we present a novel algorithm that creates and animates chimeras by dynamically reassembling source characters and their movements. Our algorithm exploits a two-network architecture: part assembler and dynamic controller. The part assembler is a supervised learning layer that searches for the spatial alignment among body parts, assuming that the temporal alignment is provided. The dynamic controller is a reinforcement learning layer that learns robust control policy for a wide variety of potential temporal alignments. These two layers are tightly intertwined and learned simultaneously. The chimera animation generated by our algorithm is energy efficient and expressive in terms of describing weight shifting, balancing, and full-body coordination. We demonstrate the versatility of our algorithm by generating the motor skills of a large variety of chimeras from limited source characters.

关键词： Physics-Based Simulation data-driven animation Deep Reinforcement Learning

来源：评论

学校读者我要写书评

暂无评论

PMP: Learning to Physically Interact with Environments using Part-wise Motion Priors 23

PMP: Learning to Physically Interact with Environments using...

引用

ACM SIGGRAPH Conference

作者： Bae, Jinseok Won, Jungdam Lim, Donggeun Min, Cheol-Hui Kim, Young Min Seoul Natl Univ Seoul South Korea

ISBN: (纸本)9798400701597

We present a method to animate a character incorporating multiple part-wise motion priors (PMP). While previous works allow creating realistic articulated motions from reference data, the range of motion is largely limited by the available samples. Especially for the interaction-rich scenarios, it is impractical to attempt acquiring every possible interacting motion, as the combination of physical parameters increases exponentially. The proposed PMP allows us to assemble multiple part skills to animate a character, creating a diverse set of motions with different combinations of existing data. In our pipeline, we can train an agent with a wide range of part-wise priors. Therefore, each body part can obtain a kinematic insight of the style from the motion captures, or at the same time extract dynamics-related information from the additional part-specific simulation. For example, we can first train a general interaction skill, e.g. grasping, only for the dexterous part, and then combine the expert trajectories from the pre-trained agent with the kinematic priors of other limbs. Eventually, our whole-body agent learns a novel physical interaction skill even with the absence of the object trajectories in the reference motion sequence.

关键词： Physics-Based Simulation data-driven animation Whole-body Control Deep Reinforcement Learning

来源：评论

学校读者我要写书评

暂无评论

Neural Face Rigging for Animating and Retargeting Facial Meshes in the Wild 23

Neural Face Rigging for Animating and Retargeting Facial Mes...

引用

ACM SIGGRAPH Conference

作者： Qin, Dafei Saito, Jun Aigerman, Noam Groueix, Thibault Komura, Taku Univ Hong Kong Hong Kong Peoples R China Adobe Res Seattle WA USA Adobe Res San Francisco CA USA

ISBN: (纸本)9798400701597

We propose an end-to-end deep-learning approach for automatic rigging and retargeting of 3D models of human faces in the wild. Our approach, called Neural Face Rigging (NFR), holds three key properties: (i) NFR's expression space maintains human-interpretable editing parameters for artistic controls;(ii) NFR is readily applicable to arbitrary facial meshes with different connectivity and expressions;(iii) NFR can encode and produce fine-grained details of complex expressions performed by arbitrary subjects. To the best of our knowledge, NFR is the first approach to provide realistic and controllable deformations of in-the-wild facial meshes, without the manual creation of blendshapes or correspondence. We design a deformation autoencoder and train it through a multi-dataset training scheme, which benefits from the unique advantages of two data sources: a linear 3DMM with interpretable control parameters as in FACS and 4D captures of real faces with fine-grained details. Through various experiments, we show NFR's ability to automatically produce realistic and accurate facial deformations across a wide range of existing datasets and noisy facial scans in-the-wild, while providing artist-controlled, editable parameters.

关键词： Facial Modeling Facial animation data-driven animation Retargeting

来源：评论

学校读者我要写书评

暂无评论

UnifiedGesture: A Unified Gesture Synthesis Model for Multiple Skeletons 23

UnifiedGesture: A Unified Gesture Synthesis Model for Multip...

引用

31st ACM International Conference on Multimedia (MM)

作者： Yang, Sicheng Wang, Zilin Wu, Zhiyong Li, Minglei Zhang, Zhensong Huang, Qiaochu Hao, Lei Xu, Songcen Wu, Xiaofei Yang, Changpeng Dai, Zonghong Tsinghua Univ Shenzhen Int Grad Sch Shenzhen Peoples R China Chinese Univ Hong Kong Hong Kong Peoples R China Huawei Cloud Comp Technol Co Ltd Shenzhen Peoples R China Huawei Noahs Ark Lab Shenzhen Peoples R China

ISBN: (纸本)9798400701085

The automatic co-speech gesture generation draws much attention in computer animation. Previous works designed network structures on individual datasets, which resulted in a lack of data volume and generalizability across different motion capture standards. In addition, it is a challenging task due to the weak correlation between speech and gestures. To address these problems, we present UnifiedGesture, a novel diffusion model-based speech-driven gesture synthesis approach, trained on multiple gesture datasets with different skeletons. Specifically, we first present a retargeting network to learn latent homeomorphic graphs for different motion capture standards, unifying the representations of various gestures while extending the dataset. We then capture the correlation between speech and gestures based on a diffusion model architecture using cross-local attention and self-attention to generate better speech-matched and realistic gestures. To further align speech and gesture and increase diversity, we incorporate reinforcement learning on the discrete gesture units with a learned reward function. Extensive experiments show that UnifiedGesture outperforms recent approaches on speech-driven gesture generation in terms of CCA, FGD, and human-likeness.

关键词： gesture generation neural motion processing data-driven animation

来源：评论

学校读者我要写书评

暂无评论

Animatomy: an Animator-centric, Anatomically Inspired System for 3D Facial Modeling, animation and Transfer 22

Animatomy: an Animator-centric, Anatomically Inspired System...

引用

SIGGRAPH Asia Conference

作者： Choi, Byungkuk Eom, Haekwang Mouscadet, Benjamin Cullingford, Stephen Ma, Kurt Gassel, Stefanie Kim, Suzi Moffat, Andrew Weta Digital Wellington New Zealand Weta FX Wellington New Zealand

ISBN: (纸本)9781450394703

We present Animatomy, a novel anatomic+animator centric representation of the human face. Present FACS-based systems are plagued with problems of face muscle separation, coverage, opposition, and redundancy. We, therefore, propose a collection of muscle fiber curves as an anatomic basis, whose contraction and relaxation provide us with a fine-grained parameterization of human facial expression. We build an end-to-end modular deformation architecture using this representation that enables: automatic optimization of the parameters of a specific face from high-quality dynamic facial scans;face animation driven by performance capture, keyframes, or dynamic simulation;interactive and direct manipulation of facial expression;and animation transfer from an actor to a character. We validate our facial system by showing compelling animated results, applications, and a quantitative comparison of our facial reconstruction to ground truth performance capture. Our system is being intensively used by a large creative team on Avatar: The Way of Water. We report feedback from these users as qualitative evaluation of our system.

关键词： Facial modeling facial expression facial animation data-driven animation animation system deformation motion capture

来源：评论

学校读者我要写书评

暂无评论

The ReprGesture entry to the GENEA Challenge 2022 22

The ReprGesture entry to the GENEA Challenge 2022

引用

24th ACM International Conference on Multimodal Interaction (ICMI)

作者： Yang, Sicheng Wu, Zhiyong Li, Minglei Zhao, Mengchen Lin, Jiuxin Chen, Liyang Bao, Weihong Tsinghua Univ Shenzhen Peoples R China Chinese Univ Hong Kong Hong Kong Peoples R China Huawei Cloud Comp Technol Co Ltd Shenzhen Peoples R China Huawei Noahs Ark Lab Shenzhen Peoples R China

ISBN: (纸本)9781450393904

This paper describes the ReprGesture entry to the Generation and Evaluation of Non-verbal Behaviour for Embodied Agents (GENEA) challenge 2022. The GENEA challenge provides the processed datasets and performs crowdsourced evaluations to compare the performance of different gesture generation systems. In this paper, we explore an automatic gesture generation system based on multimodal representation learning. We use WavLM features for audio, FastText features for text and position and rotation matrix features for gesture. Each modality is projected to two distinct subspaces: modality-invariant and modality-specific. To learn inter-modality-invariant commonalities and capture the characters of modality-specific representations, gradient reversal layer based adversarial classifier and modality reconstruction decoders are used during training. The gesture decoder generates proper gestures using all representations and features related to the rhythm in the audio. Our code, pre-trained models and demo are available at https://***/YoungSeng/ReprGesture.

关键词： gesture generation data-driven animation modality-invaiant modality-specific representation learning deep learning

来源：评论

学校读者我要写书评

暂无评论

Learning a family of motor skills from a single motion clip

引用

ACM TRANSACTIONS ON GRAPHICS 2021年第4期40卷 1-13页

作者： Lee, Seyoung Lee, Sunmin Lee, Yongwoo Lee, Jehee Seoul Natl Univ Dept Comp Sci & Engn Seoul South Korea

We present a new algorithm that learns a parameterized family of motor skills from a single motion clip. The motor skills are represented by a deep policy network, which produces a stream of motions in physics simulation in response to user input and environment interaction by navigating continuous action space. Three novel technical components play an important role in the success of our algorithm. First, it explicitly constructs motion parameterization that maps action parameters to their corresponding motions. Simultaneous learning of motion parameterization and motor skills significantly improves the performance and visual quality of learned motor skills. Second, continuous-time reinforcement learning is adopted to explore temporal variations as well as spatial variations in motion parameterization. Lastly, we present a new automatic curriculum generation method that explores continuous action space more efficiently. We demonstrate the flexibility and versatility of our algorithm with highly dynamic motor skills that can be parameterized by task goals, body proportions, physical measurements, and environmental conditions.

关键词： Learning Motor Skills Physics-Based Simulation data-driven animation Deep Reinforcement Learning

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：