Guardado en:
Detalles Bibliográficos
Autores principales: Li, Ling, Chen, Changjie, Wang, Yuyan, Lyu, Jiaqing, Chang, Kenglun, Chen, Yiyun, Deng, Zhidong
Formato: Preprint
Publicado: 2026
Materias:
Acceso en línea:https://arxiv.org/abs/2605.14525
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866913127412531200
author Li, Ling
Chen, Changjie
Wang, Yuyan
Lyu, Jiaqing
Chang, Kenglun
Chen, Yiyun
Deng, Zhidong
author_facet Li, Ling
Chen, Changjie
Wang, Yuyan
Lyu, Jiaqing
Chang, Kenglun
Chen, Yiyun
Deng, Zhidong
contents In multi-view 3D human pose estimation, models typically rely on images captured simultaneously from different camera views to predict a pose at a specific moment. While providing accurate spatial information, this traditional approach often overlooks the rich temporal dependencies between adjacent frames. We propose a novel 3D human pose estimation input method: the sparse interleaved input to address this. This method leverages images captured from different camera views at various time points (e.g., View 1 at time $t$ and View 2 at time $t+δ$), allowing our model to capture rich spatio-temporal information and effectively boost performance. More importantly, this approach offers two key advantages: First, it can theoretically increase the output pose frame rate by N times with N cameras, thereby breaking through single-view frame rate limitations and enhancing the temporal resolution of the production. Second, using a sparse subset of available frames, our method can reduce data redundancy and simultaneously achieve better performance. We introduce the DenseWarper model, which leverages epipolar geometry for efficient spatio-temporal heatmap exchange. We conducted extensive experiments on the Human3.6M and MPI-INF-3DHP datasets. Results demonstrate that our method, utilizing only sparse interleaved images as input, outperforms traditional dense multi-view input approaches and achieves state-of-the-art performance. The source code for this work is available at: https://github.com/lingli1724/DenseWarper-ICLR2026
format Preprint
id arxiv_https___arxiv_org_abs_2605_14525
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle From Sparse to Dense: Spatio-Temporal Fusion for Multi-View 3D Human Pose Estimation with DenseWarper
Li, Ling
Chen, Changjie
Wang, Yuyan
Lyu, Jiaqing
Chang, Kenglun
Chen, Yiyun
Deng, Zhidong
Computer Vision and Pattern Recognition
In multi-view 3D human pose estimation, models typically rely on images captured simultaneously from different camera views to predict a pose at a specific moment. While providing accurate spatial information, this traditional approach often overlooks the rich temporal dependencies between adjacent frames. We propose a novel 3D human pose estimation input method: the sparse interleaved input to address this. This method leverages images captured from different camera views at various time points (e.g., View 1 at time $t$ and View 2 at time $t+δ$), allowing our model to capture rich spatio-temporal information and effectively boost performance. More importantly, this approach offers two key advantages: First, it can theoretically increase the output pose frame rate by N times with N cameras, thereby breaking through single-view frame rate limitations and enhancing the temporal resolution of the production. Second, using a sparse subset of available frames, our method can reduce data redundancy and simultaneously achieve better performance. We introduce the DenseWarper model, which leverages epipolar geometry for efficient spatio-temporal heatmap exchange. We conducted extensive experiments on the Human3.6M and MPI-INF-3DHP datasets. Results demonstrate that our method, utilizing only sparse interleaved images as input, outperforms traditional dense multi-view input approaches and achieves state-of-the-art performance. The source code for this work is available at: https://github.com/lingli1724/DenseWarper-ICLR2026
title From Sparse to Dense: Spatio-Temporal Fusion for Multi-View 3D Human Pose Estimation with DenseWarper
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2605.14525