DANBO: Disentangled Articulated Neural Body Representations via Graph Neural Networks

Su, Shih-Yang; Bagautdinov, Timur; Rhodin, Helge

doi:10.1007/978-3-031-20086-1_7

Cited by 25 publications

(6 citation statements)

References 50 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Our approach falls into the paradigm of using neural fields for articulated object reconstruction and further learns a complete system for detection, pose estimation, and articulated shape reconstruction from a single observation. Implicit Reconstruction of Non-Rigid Objects: Going beyond static scenes with rigid objects, [1] handle dynamic scenes while [27,33] focus on reconstructing humans by leveraging their strong shape and kinematic prior as well as the amount of readily available datasets. [42] propose a general reconstruction framework to reconstruct any nonrigid entity (i.e.…”

Section: Related Workmentioning

confidence: 99%

CARTO: Category and Joint Agnostic Reconstruction of ARTiculated Objects

Nick¹,

Irshad²,

Захаров³

et al. 2023

Preprint

View full text Add to dashboard Cite

show abstract

Section: Related Workmentioning

confidence: 99%

CARTO: Category and Joint Agnostic Reconstruction of ARTiculated Objects

Nick¹,

Irshad²,

Захаров³

et al. 2023

Preprint

View full text Add to dashboard Cite

show abstract

“…With the significant success of NeRF [MST*21] in recent years, there have also been NeRF‐Based methods [SYZR21,SBR22] that produce high‐quality reconstruction results through neural rendering.…”

Section: Related Workmentioning

confidence: 99%

Multi‐Level Implicit Function for Detailed Human Reconstruction by Relaxing SMPL Constraints

Ma,

Zhao,

Teng

et al. 2023

Computer Graphics Forum

View full text Add to dashboard Cite

Aiming at enhancing the rationality and robustness of the results of single‐view image‐based human reconstruction and acquiring richer surface details, we propose a multi‐level reconstruction framework based on implicit functions. This framework first utilizes the predicted SMPL model (Skinned Multi‐Person Linear Model) as a prior to further predict consistent 2.5D sketches (depth map and normal map), and then obtains a coarse reconstruction result through an Implicit Function fitting network (IF‐Net). Subsequently, with a pixel‐aligned feature extraction module and a fine IF‐Net, the strong constraints imposed by SMPL are relaxed to add more surface details to the reconstruction result and remove noise. Finally, to address the trade‐off between surface details and rationality under complex poses, we propose a novel fusion repair algorithm that reuses existing information. This algorithm compensates for the missing parts of the fine reconstruction results with the coarse reconstruction results, leading to a robust, rational, and richly detailed reconstruction. The final experiments prove the effectiveness of our method and demonstrate that it achieves the richest surface details while ensuring rationality. The project website can be found at https://github.com/MXKKK/2.5D‐MLIF.

show abstract

“…As mitigating the costly hardware requirement, they estimate a 3D human texture (Xu and Loy, 2021;Gomes et al, 2022) via the UV mapping (Shysheya et al, 2019;Yoon et al, 2021). With the promising success of NeRF, recent works (Peng et al, 2021b,a;Su et al, 2021) adopt volume rendering for 3D humans from multi-view videos (Weng et al, 2022;. Since the data are difficult to collect, the 3D-aware generation (Chan et al, 2022;Gu et al, 2022;Noguchi et al, 2022) learns 3D modeling from the collection of human images Hong et al, 2023).…”

Section: Related Workmentioning

confidence: 99%

Text-guided 3D Human Generation from 2D Collections

Fu,

Xiong,

Nie

et al. 2023

Findings of the Association for Computational Linguistics: EMNLP 2023

View full text Add to dashboard Cite

3D human modeling has been widely used for engaging interaction in gaming, film, and animation. The customization of these characters is crucial for creativity and scalability, which highlights the importance of controllability. In this work, we introduce Text-guided 3D Human Generation (T3H), where a model is to generate a 3D human, guided by the fashion description. There are two goals: 1) the 3D human should render articulately, and 2) its outfit is controlled by the given text. To address this T3H task, we propose Compositional Cross-modal Human (CCH). CCH adopts cross-modal attention to fuse compositional human rendering with the extracted fashion semantics. Each human body part perceives relevant textual guidance as its visual patterns. We incorporate the human prior and semantic discrimination to enhance 3D geometry transformation and fine-grained consistency, enabling this to learn from 2D collections for data efficiency. We conduct evaluations on DeepFashion and SHHQ with diverse fashion attributes covering the shape, fabric, and color of upper and lower clothing. Extensive experiments demonstrate that CCH achieves superior results for T3H with high efficiency.

show abstract

DANBO: Disentangled Articulated Neural Body Representations via Graph Neural Networks

Cited by 25 publications

References 50 publications

CARTO: Category and Joint Agnostic Reconstruction of ARTiculated Objects

CARTO: Category and Joint Agnostic Reconstruction of ARTiculated Objects

Multi‐Level Implicit Function for Detailed Human Reconstruction by Relaxing SMPL Constraints

Text-guided 3D Human Generation from 2D Collections

Contact Info

Product

Resources

About