Skip to Main content Skip to Navigation
Conference papers

Leveraging Photometric Consistency over Time for Sparsely Supervised Hand-Object Reconstruction

Abstract : Modeling hand-object manipulations is essential for understanding how humans interact with their environment. While of practical importance, estimating the pose of hands and objects during interactions is challenging due to the large mutual occlusions that occur during manipulation. Recent efforts have been directed towards fully-supervised methods that require large amounts of labeled training samples. Collecting 3D ground-truth data for hand-object interactions, however, is costly, tedious, and error-prone. To overcome this challenge we present a method to leverage photometric consistency across time when annotations are only available for a sparse subset of frames in a video. Our model is trained end-to-end on color images to jointly reconstruct hands and objects in 3D by inferring their poses. Given our estimated reconstructions, we differentiably render the optical flow between pairs of adjacent images and use it within the network to warp one frame to another. We then apply a self-supervised photometric loss that relies on the visual consistency between nearby images. We achieve state-of-the-art results on 3D hand-object reconstruction benchmarks and demonstrate that our approach allows us to improve the pose estimation accuracy by leveraging information from neighboring frames in low-data regimes.
Document type :
Conference papers
Complete list of metadatas

Cited literature [56 references]  Display  Hide  Download
Contributor : Yana Hasson <>
Submitted on : Tuesday, April 28, 2020 - 2:40:53 PM
Last modification on : Tuesday, January 5, 2021 - 9:52:57 AM


Files produced by the author(s)


  • HAL Id : hal-02557112, version 1



Yana Hasson, Bugra Tekin, Federica Bogo, Ivan Laptev, Marc Pollefeys, et al.. Leveraging Photometric Consistency over Time for Sparsely Supervised Hand-Object Reconstruction. CVPR 2020 - IEEE Conference on Computer Vision and Pattern Recognition, Jun 2020, Seattle / Virtual, United States. pp.1-12. ⟨hal-02557112⟩



Record views


Files downloads