Skip to Main content Skip to Navigation
Preprints, Working Papers, ...

Monocular Human Shape and Pose with Dense Mesh-borne Local Image Features

Shubhendu Jena 1 Franck Multon 1, 2 Adnane Boukhayma 1
1 MIMETIC - Analysis-Synthesis Approach for Virtual Human Simulation
UR2 - Université de Rennes 2, Inria Rennes – Bretagne Atlantique , IRISA-D6 - MEDIA ET INTERACTIONS
Abstract : We propose to improve on graph convolution based approaches for human shape and pose estimation from monocular input, using pixel-aligned local image features. Given a single input color image, existing graph convolutional network (GCN) based techniques for human shape and pose estimation (e.g. [19]) use a single convolutional neural network (CNN) generated global image feature appended to all mesh vertices equally to initialize the GCN stage, which transforms a template T-posed mesh into the target pose. In contrast, we propose for the first time the idea of using local image features per vertex. These features are sampled from the CNN image feature maps by utilizing pixel-to-mesh correspondences generated with DensePose [11]. Our quantitative and qualitative results on standard benchmarks show that using local features improves on global ones and leads to competitive performances with respect to the state-of-the-art.
Document type :
Preprints, Working Papers, ...
Complete list of metadata

https://hal.inria.fr/hal-03462789
Contributor : Franck Multon Connect in order to contact the contributor
Submitted on : Thursday, December 2, 2021 - 9:35:49 AM
Last modification on : Tuesday, January 4, 2022 - 5:53:45 AM

File

2111.05319.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-03462789, version 1

Citation

Shubhendu Jena, Franck Multon, Adnane Boukhayma. Monocular Human Shape and Pose with Dense Mesh-borne Local Image Features. 2021. ⟨hal-03462789⟩

Share

Metrics

Les métriques sont temporairement indisponibles