Learning joint reconstruction of hands and manipulated objects

Abstract : Estimating hand-object manipulations is essential for interpreting and imitating human actions. Previous work has made significant progress towards reconstruction of hand poses and object shapes in isolation. Yet, reconstructing hands and objects during manipulation is a more challenging task due to significant occlusions of both the hand and object. While presenting challenges, manipulations may also simplify the problem since the physics of contact restricts the space of valid hand-object configurations. For example, during manipulation, the hand and object should be in contact but not interpenetrate. In this work, we regularize the joint reconstruction of hands and objects with manipulation constraints. We present an end-to-end learnable model that exploits a novel contact loss that favors physically plausible hand-object constellations. Our approach improves grasp quality metrics over baselines, using RGB images as input. To train and evaluate the model, we also propose a new large-scale synthetic dataset, ObMan, with hand-object manipulations. We demonstrate the transferability of ObMan-trained models to real data.
Complete list of metadatas

Cited literature [80 references]  Display  Hide  Download

https://hal.archives-ouvertes.fr/hal-02429093
Contributor : Yana Hasson <>
Submitted on : Monday, January 6, 2020 - 2:04:52 PM
Last modification on : Thursday, January 23, 2020 - 12:10:12 PM

File

hassonCVPR2019.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-02429093, version 1

Collections

Citation

Yana Hasson, Gül Varol, Dimitrios Tzionas, Igor Kalevatykh, Michael Black, et al.. Learning joint reconstruction of hands and manipulated objects. CVPR 2019 - IEEE Conference on Computer Vision and Pattern Recognition, Jun 2019, Long Beach, United States. pp.1-14. ⟨hal-02429093⟩

Share

Metrics

Record views

34

Files downloads

29