Home > Research > Publications & Outputs > A probabilistic attention model with occlusion-...

Electronic data

Links

Text available via DOI:

View graph of relations

A probabilistic attention model with occlusion-aware texture regression for 3D hand reconstruction from a single RGB image

Research output: Contribution in Book/Report/Proceedings - With ISBN/ISSNConference contribution/Paperpeer-review

Published

Standard

A probabilistic attention model with occlusion-aware texture regression for 3D hand reconstruction from a single RGB image. / Jiang, Zheheng; Rahmani, Hossein; Black, S. et al.
Proceedings - 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2023. IEEE, 2023. p. 758-767 (Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition; Vol. 2023-June).

Research output: Contribution in Book/Report/Proceedings - With ISBN/ISSNConference contribution/Paperpeer-review

Harvard

Jiang, Z, Rahmani, H, Black, S & Williams, B 2023, A probabilistic attention model with occlusion-aware texture regression for 3D hand reconstruction from a single RGB image. in Proceedings - 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2023. Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, vol. 2023-June, IEEE, pp. 758-767. https://doi.org/10.1109/CVPR52729.2023.00080

APA

Jiang, Z., Rahmani, H., Black, S., & Williams, B. (2023). A probabilistic attention model with occlusion-aware texture regression for 3D hand reconstruction from a single RGB image. In Proceedings - 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2023 (pp. 758-767). (Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition; Vol. 2023-June). IEEE. https://doi.org/10.1109/CVPR52729.2023.00080

Vancouver

Jiang Z, Rahmani H, Black S, Williams B. A probabilistic attention model with occlusion-aware texture regression for 3D hand reconstruction from a single RGB image. In Proceedings - 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2023. IEEE. 2023. p. 758-767. (Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition). doi: 10.1109/CVPR52729.2023.00080

Author

Jiang, Zheheng ; Rahmani, Hossein ; Black, S. et al. / A probabilistic attention model with occlusion-aware texture regression for 3D hand reconstruction from a single RGB image. Proceedings - 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2023. IEEE, 2023. pp. 758-767 (Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition).

Bibtex

@inproceedings{bd11a7615a144339927ada697ef42fd8,
title = "A probabilistic attention model with occlusion-aware texture regression for 3D hand reconstruction from a single RGB image",
abstract = "Recently, deep learning based approaches have shown promising results in 3D hand reconstruction from a single RGB image. These approaches can be roughly divided into model-based approaches, which are heavily dependent on the model's parameter space, and model-free approaches, which require large numbers of 3D ground truths to reduce depth ambiguity and struggle in weakly-supervised scenarios. To overcome these issues, we propose a novel probabilistic model to achieve the robustness of model-based approaches and reduced dependence on the model's parameter space of model-free approaches. The proposed probabilistic model incorporates a model-based network as a prior-net to estimate the prior probability distribution of joints and vertices. An Attention-based Mesh Vertices Uncertainty Regression (AMVUR) model is proposed to capture dependencies among vertices and the correlation between joints and mesh vertices to improve their feature representation. We further propose a learning based occlusion-aware Hand Texture Regression model to achieve high-fidelity texture reconstruction. We demonstrate the flexibility of the proposed probabilistic model to be trained in both supervised and weakly-supervised scenarios. The experimental results demonstrate our probabilistic model's state-of-the-art accuracy in 3D hand and texture reconstruction from a single image in both training schemes, including in the presence of severe occlusions.",
author = "Zheheng Jiang and Hossein Rahmani and S. Black and Bryan Williams",
year = "2023",
month = jun,
day = "23",
doi = "10.1109/CVPR52729.2023.00080",
language = "English",
series = "Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition",
publisher = "IEEE",
pages = "758--767",
booktitle = "Proceedings - 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2023",

}

RIS

TY - GEN

T1 - A probabilistic attention model with occlusion-aware texture regression for 3D hand reconstruction from a single RGB image

AU - Jiang, Zheheng

AU - Rahmani, Hossein

AU - Black, S.

AU - Williams, Bryan

PY - 2023/6/23

Y1 - 2023/6/23

N2 - Recently, deep learning based approaches have shown promising results in 3D hand reconstruction from a single RGB image. These approaches can be roughly divided into model-based approaches, which are heavily dependent on the model's parameter space, and model-free approaches, which require large numbers of 3D ground truths to reduce depth ambiguity and struggle in weakly-supervised scenarios. To overcome these issues, we propose a novel probabilistic model to achieve the robustness of model-based approaches and reduced dependence on the model's parameter space of model-free approaches. The proposed probabilistic model incorporates a model-based network as a prior-net to estimate the prior probability distribution of joints and vertices. An Attention-based Mesh Vertices Uncertainty Regression (AMVUR) model is proposed to capture dependencies among vertices and the correlation between joints and mesh vertices to improve their feature representation. We further propose a learning based occlusion-aware Hand Texture Regression model to achieve high-fidelity texture reconstruction. We demonstrate the flexibility of the proposed probabilistic model to be trained in both supervised and weakly-supervised scenarios. The experimental results demonstrate our probabilistic model's state-of-the-art accuracy in 3D hand and texture reconstruction from a single image in both training schemes, including in the presence of severe occlusions.

AB - Recently, deep learning based approaches have shown promising results in 3D hand reconstruction from a single RGB image. These approaches can be roughly divided into model-based approaches, which are heavily dependent on the model's parameter space, and model-free approaches, which require large numbers of 3D ground truths to reduce depth ambiguity and struggle in weakly-supervised scenarios. To overcome these issues, we propose a novel probabilistic model to achieve the robustness of model-based approaches and reduced dependence on the model's parameter space of model-free approaches. The proposed probabilistic model incorporates a model-based network as a prior-net to estimate the prior probability distribution of joints and vertices. An Attention-based Mesh Vertices Uncertainty Regression (AMVUR) model is proposed to capture dependencies among vertices and the correlation between joints and mesh vertices to improve their feature representation. We further propose a learning based occlusion-aware Hand Texture Regression model to achieve high-fidelity texture reconstruction. We demonstrate the flexibility of the proposed probabilistic model to be trained in both supervised and weakly-supervised scenarios. The experimental results demonstrate our probabilistic model's state-of-the-art accuracy in 3D hand and texture reconstruction from a single image in both training schemes, including in the presence of severe occlusions.

U2 - 10.1109/CVPR52729.2023.00080

DO - 10.1109/CVPR52729.2023.00080

M3 - Conference contribution/Paper

T3 - Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition

SP - 758

EP - 767

BT - Proceedings - 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2023

PB - IEEE

ER -