NSTL国家科技图书文献中心

1. 3D human avatar reconstruction with neural fields: A recent survey NSTL国家科技图书文献中心

Gu, Meiying | Li, Jiahe ... - 《Image and vision computing》 - 2025,154(Feb.) - 1.1～1.27 - 共27页

摘要：3D human avatar* reconstruction aims to* | overview of 3D human avatar* reconstruction methods using* | background of 3D human avatar* reconstruction and the* | representation and avatar* partswith detailed discussion* | reconstruct the 3D geometric shape and appearance of the

关键词： 3D human reconstruction | Neural fields | Literature survey | FIDELITY HEAD AVATAR | RADIANCE FIELDS | REPRESENTATION | MESH

2. Portrait4D-V2: Pseudo Multi-view Data Creates Better 4D Head Synthesizer NSTL国家科技图书文献中心

Yu Deng | Duomin Wang ... - 《Computer Vision - ECCV 2024,Part XVII》 - European Conference on Computer Vision - 2025, - 316～333 - 共18页

摘要： approach for feedforward one-shot 4D head avatar | for improved 4D head* avatar creation.* | 4D head* synthesizer in a data-driven manner* | key idea is to first learn a 3D head* synthesizer* | the pseudo multi-view videos to learn a 4D head

关键词： Head avatar | Video reenactment | NeRF

3. THGS: Lifelike Talking Human Avatar Synthesis From Monocular Video Via 3D Gaussian Splatting NSTL国家科技图书文献中心

Chen, Chuang | Yu, Lingyun ... - 《Computer Graphics Forum》 - 2025,44(1) - n/a～n/a - 共17页

摘要： head generation, directly generating 3D talking human | this paper, we extend speaker-specific talking head | generation task to talking human avatar* synthesis and* | by linearly combining the static head* model and* | that THGS can achieve high-fidelity* 3D talking human*

关键词： image and video processing | real-time rendering | monocular re-construction | 3D Gaussian Splatting | real‐time rendering | monocular re‐construction

4. Gaussian Head Avatar: Ultra High-Fidelity Head Avatar via Dynamic Gaussians NSTL国家科技图书文献中心

Yuelang Xu | Bengwang Chen ... - 《2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition》 - IEEE/CVF Conference on Computer Vision and Pattern Recognition - 2024, - 1931～1941 - 共11页

摘要：Creating high-fidelity* 3D head avatars has* | . In this paper, we propose Gaussian Head Avatar | head avatar modeling. We optimize the neutral 3D | represented by controllable 3D Gaussians for high-fidelity | methods, achieving ultra high-fidelity* rendering quality*

关键词： Training | Solid modeling | Head | Three-dimensional displays | Deformation | Avatars | Rendering (computer graphics)

5. FlashAvatar: High-Fidelity Head Avatar with Efficient Gaussian Embedding NSTL国家科技图书文献中心

Jun Xiang | Xuan Gao ... - 《2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition》 - IEEE/CVF Conference on Computer Vision and Pattern Recognition - 2024, - 1802～1812 - 共11页

摘要： lightweight 3D animatable avatar* representation that could* | reconstruct a digital avatar* from a short monocular video* | sequence in minutes and render high-fidelity* photo* | We propose FlashAvatar, a novel and | -realistic images at 300FPS on a consumer-grade GPU. To

关键词： Solid modeling | Surface reconstruction | Three-dimensional displays | Head | Avatars | Video sequences | Graphics processing units

6. Generating Look-Alike Avatars: Perception of Head Shape, Texture Fidelity and Head Orientation of Another User's Look-Alike Avatar NSTL国家科技图书文献中心

Kwame Agyemang Baffo... | Oyewole Oyekoya - 《2024 IEEE Conference on Virtual Reality and 3D User Interfaces Abstracts and Workshops: VRW 2024, Orlando, Florida, USA, 16-21 March 2024, [v.1]》 - IEEE Conference on Virtual Reality and 3D User Interfaces - 2024, - 983～984 - 共2页

摘要： determine the influence of head shape, texture fidelity | and head* orientation of a look-alike avatar on* | different head* orientations (0°, 45°, 90°) of the look* | head silhouettes, to emphasize the differences in | head shapes. Results suggest that participants prefer

关键词： Visualization | Head | Three-dimensional displays | Shape | Avatars | Conferences | Virtual environments

7. Sem-Avatar: Semantic Controlled Neural Field for High-Fidelity Audio Driven Avatar NSTL国家科技图书文献中心

Xiang Zhou | Weichen Zhang ... - 《Pattern Recognition and Computer Vision: 6th Chinese Conference, PRCV 2023, Xiamen, China, October 13-15, 2023, Proceedings, Part II》 - Chinese Conference on Pattern Recognition and Computer Vision - 2024, - 66～78 - 共13页

摘要： the above problems, delievering high-fidelity avatar | avatar challenge by fitting a semantic controlled | neural field to a talking-head* video. While existing* | methods struggle with realism and head-torso | controlled neural field (Sem-Avatar) sucessfully overcomes

关键词： Avatar synthesis | Talking head | Neural rendering

8. Semantic-aware hyper-space deformable neural radiance fields for facial avatar reconstruction NSTL国家科技图书文献中心

Jin K. | Gu X.... - 《Pattern recognition letters》 - 2024,185(Sep.) - 160～166 - 共7页

摘要：? 2024 Elsevier B.V.High-fidelity* facial* | avatar reconstruction from monocular videos is a | for its potential in facial avatar* reconstruction* | complex motion dynamics present across the head, torso | facial avatar* reconstruction adaptable to either 3DMM*

关键词： Facial avatar reconstruction | Hyper-space deformation | Neural radiance fields | Semantic guidance

9. A3RT: Attention-Aware AR Teleconferencing with Life-Size 2.5D Video Avatars NSTL国家科技图书文献中心

Xuanyu Wang | Weizhan Zhang ... - 《2024 IEEE Conference Virtual Reality and 3D User Interfaces: VR 2024, Orlando, Florida, USA, 16-21 March 2024, [v.1]》 - IEEE Conference Virtual Reality and 3D User Interfaces - 2024, - 211～221 - 共11页

摘要：-avatar-based approach has the advantage of balancing | fidelity and the sense of co-presence using easy-to-setup | devices, including only a camera and an AR Head-Mounted | additional hardware, or alter to use a virtual avatar | lose the fidelity* of remote users’ authentic*

关键词： Teleconferencing | Visualization | Three-dimensional displays | Head-mounted displays | Avatars | Layout | Prototypes

10. Repeat Body-Ownership Illusions in Commodity Virtual Reality NSTL国家科技图书文献中心

Pauline W. Cha | Tabitha C. Peck - 《2024 IEEE Conference on Virtual Reality and 3D User Interfaces Abstracts and Workshops: VRW 2024, Orlando, Florida, USA, 16-21 March 2024, [v.1]》 - IEEE Conference on Virtual Reality and 3D User Interfaces - 2024, - 825～826 - 共2页

摘要： participants are given a self-avatar* in a simple virtual* | experience while wearing a cardboard head-mounted display | those reported in experience using higher-fidelity | Virtual self-avatars have been shown to | produce the Proteus effect, however limited work

摘要：3D human avatar* reconstruction aims to* | overview of 3D human avatar* reconstruction methods using* | background of 3D human avatar* reconstruction and the* | representation and avatar* partswith detailed discussion* | reconstruct the 3D geometric shape and appearance of the

关键词： 3D human reconstruction | Neural fields | Literature survey | FIDELITY HEAD AVATAR | RADIANCE FIELDS | REPRESENTATION | MESH

摘要： approach for feedforward one-shot 4D head avatar | for improved 4D head* avatar creation.* | 4D head* synthesizer in a data-driven manner* | key idea is to first learn a 3D head* synthesizer* | the pseudo multi-view videos to learn a 4D head

关键词： Head avatar | Video reenactment | NeRF

摘要： head generation, directly generating 3D talking human | this paper, we extend speaker-specific talking head | generation task to talking human avatar* synthesis and* | by linearly combining the static head* model and* | that THGS can achieve high-fidelity* 3D talking human*

关键词： image and video processing | real-time rendering | monocular re-construction | 3D Gaussian Splatting | real‐time rendering | monocular re‐construction

摘要：Creating high-fidelity* 3D head avatars has* | . In this paper, we propose Gaussian Head Avatar | head avatar modeling. We optimize the neutral 3D | represented by controllable 3D Gaussians for high-fidelity | methods, achieving ultra high-fidelity* rendering quality*

关键词： Training | Solid modeling | Head | Three-dimensional displays | Deformation | Avatars | Rendering (computer graphics)

摘要： lightweight 3D animatable avatar* representation that could* | reconstruct a digital avatar* from a short monocular video* | sequence in minutes and render high-fidelity* photo* | We propose FlashAvatar, a novel and | -realistic images at 300FPS on a consumer-grade GPU. To

关键词： Solid modeling | Surface reconstruction | Three-dimensional displays | Head | Avatars | Video sequences | Graphics processing units

摘要： determine the influence of head shape, texture fidelity | and head* orientation of a look-alike avatar on* | different head* orientations (0°, 45°, 90°) of the look* | head silhouettes, to emphasize the differences in | head shapes. Results suggest that participants prefer

关键词： Visualization | Head | Three-dimensional displays | Shape | Avatars | Conferences | Virtual environments

摘要： the above problems, delievering high-fidelity avatar | avatar challenge by fitting a semantic controlled | neural field to a talking-head* video. While existing* | methods struggle with realism and head-torso | controlled neural field (Sem-Avatar) sucessfully overcomes

关键词： Avatar synthesis | Talking head | Neural rendering

摘要：? 2024 Elsevier B.V.High-fidelity* facial* | avatar reconstruction from monocular videos is a | for its potential in facial avatar* reconstruction* | complex motion dynamics present across the head, torso | facial avatar* reconstruction adaptable to either 3DMM*

关键词： Facial avatar reconstruction | Hyper-space deformation | Neural radiance fields | Semantic guidance

摘要：-avatar-based approach has the advantage of balancing | fidelity and the sense of co-presence using easy-to-setup | devices, including only a camera and an AR Head-Mounted | additional hardware, or alter to use a virtual avatar | lose the fidelity* of remote users’ authentic*

关键词： Teleconferencing | Visualization | Three-dimensional displays | Head-mounted displays | Avatars | Layout | Prototypes

摘要： participants are given a self-avatar* in a simple virtual* | experience while wearing a cardboard head-mounted display | those reported in experience using higher-fidelity | Virtual self-avatars have been shown to | produce the Proteus effect, however limited work

关键词： Three-dimensional displays | Head-mounted displays | Design methodology | Conferences | Virtual reality | User interfaces

4008-161-200 800-990-8900

国家科技图书文献中心

摘要：3D human avatar reconstruction aims to | overview of 3D human avatar reconstruction methods using | background of 3D human avatar reconstruction and the | representation and avatar partswith detailed discussion | reconstruct the 3D geometric shape and appearance of the

关键词： 3D human reconstruction | Neural fields | Literature survey | FIDELITY HEAD AVATAR | RADIANCE FIELDS | REPRESENTATION | MESH

摘要： approach for feedforward one-shot 4D head avatar | for improved 4D head avatar creation. | 4D head synthesizer in a data-driven manner | key idea is to first learn a 3D head synthesizer | the pseudo multi-view videos to learn a 4D head

关键词： Head avatar | Video reenactment | NeRF

摘要： head generation, directly generating 3D talking human | this paper, we extend speaker-specific talking head | generation task to talking human avatar synthesis and | by linearly combining the static head model and | that THGS can achieve high-fidelity 3D talking human

关键词： image and video processing | real-time rendering | monocular re-construction | 3D Gaussian Splatting | real‐time rendering | monocular re‐construction

摘要：Creating high-fidelity 3D head avatars has | . In this paper, we propose Gaussian Head Avatar | head avatar modeling. We optimize the neutral 3D | represented by controllable 3D Gaussians for high-fidelity | methods, achieving ultra high-fidelity rendering quality

关键词： Training | Solid modeling | Head | Three-dimensional displays | Deformation | Avatars | Rendering (computer graphics)

摘要： lightweight 3D animatable avatar representation that could | reconstruct a digital avatar from a short monocular video | sequence in minutes and render high-fidelity photo | We propose FlashAvatar, a novel and | -realistic images at 300FPS on a consumer-grade GPU. To

关键词： Solid modeling | Surface reconstruction | Three-dimensional displays | Head | Avatars | Video sequences | Graphics processing units

摘要： determine the influence of head shape, texture fidelity | and head orientation of a look-alike avatar on | different head orientations (0°, 45°, 90°) of the look | head silhouettes, to emphasize the differences in | head shapes. Results suggest that participants prefer

关键词： Visualization | Head | Three-dimensional displays | Shape | Avatars | Conferences | Virtual environments

摘要： the above problems, delievering high-fidelity avatar | avatar challenge by fitting a semantic controlled | neural field to a talking-head video. While existing | methods struggle with realism and head-torso | controlled neural field (Sem-Avatar) sucessfully overcomes

关键词： Avatar synthesis | Talking head | Neural rendering

摘要：? 2024 Elsevier B.V.High-fidelity facial | avatar reconstruction from monocular videos is a | for its potential in facial avatar reconstruction | complex motion dynamics present across the head, torso | facial avatar reconstruction adaptable to either 3DMM

关键词： Facial avatar reconstruction | Hyper-space deformation | Neural radiance fields | Semantic guidance

摘要：-avatar-based approach has the advantage of balancing | fidelity and the sense of co-presence using easy-to-setup | devices, including only a camera and an AR Head-Mounted | additional hardware, or alter to use a virtual avatar | lose the fidelity of remote users’ authentic

关键词： Teleconferencing | Visualization | Three-dimensional displays | Head-mounted displays | Avatars | Layout | Prototypes

摘要： participants are given a self-avatar in a simple virtual | experience while wearing a cardboard head-mounted display | those reported in experience using higher-fidelity | Virtual self-avatars have been shown to | produce the Proteus effect, however limited work

关键词： Three-dimensional displays | Head-mounted displays | Design methodology | Conferences | Virtual reality | User interfaces

4008-161-200 800-990-8900

国家科技图书文献中心

摘要：3D human avatar* reconstruction aims to* | overview of 3D human avatar* reconstruction methods using* | background of 3D human avatar* reconstruction and the* | representation and avatar* partswith detailed discussion* | reconstruct the 3D geometric shape and appearance of the

摘要： approach for feedforward one-shot 4D head avatar | for improved 4D head* avatar creation.* | 4D head* synthesizer in a data-driven manner* | key idea is to first learn a 3D head* synthesizer* | the pseudo multi-view videos to learn a 4D head

摘要： head generation, directly generating 3D talking human | this paper, we extend speaker-specific talking head | generation task to talking human avatar* synthesis and* | by linearly combining the static head* model and* | that THGS can achieve high-fidelity* 3D talking human*

摘要：Creating high-fidelity* 3D head avatars has* | . In this paper, we propose Gaussian Head Avatar | head avatar modeling. We optimize the neutral 3D | represented by controllable 3D Gaussians for high-fidelity | methods, achieving ultra high-fidelity* rendering quality*

摘要： lightweight 3D animatable avatar* representation that could* | reconstruct a digital avatar* from a short monocular video* | sequence in minutes and render high-fidelity* photo* | We propose FlashAvatar, a novel and | -realistic images at 300FPS on a consumer-grade GPU. To

摘要： determine the influence of head shape, texture fidelity | and head* orientation of a look-alike avatar on* | different head* orientations (0°, 45°, 90°) of the look* | head silhouettes, to emphasize the differences in | head shapes. Results suggest that participants prefer

摘要： the above problems, delievering high-fidelity avatar | avatar challenge by fitting a semantic controlled | neural field to a talking-head* video. While existing* | methods struggle with realism and head-torso | controlled neural field (Sem-Avatar) sucessfully overcomes

摘要：? 2024 Elsevier B.V.High-fidelity* facial* | avatar reconstruction from monocular videos is a | for its potential in facial avatar* reconstruction* | complex motion dynamics present across the head, torso | facial avatar* reconstruction adaptable to either 3DMM*

摘要：-avatar-based approach has the advantage of balancing | fidelity and the sense of co-presence using easy-to-setup | devices, including only a camera and an AR Head-Mounted | additional hardware, or alter to use a virtual avatar | lose the fidelity* of remote users’ authentic*

摘要： participants are given a self-avatar* in a simple virtual* | experience while wearing a cardboard head-mounted display | those reported in experience using higher-fidelity | Virtual self-avatars have been shown to | produce the Proteus effect, however limited work