Dense Pose Transfer

Natalia Neverova (1) , Riza Alp Güler (2, 3) , Iasonas Kokkinos (4)

1 FAIR - Facebook AI Research [Paris]
2 CVN - Centre de vision numérique
3 GALEN-POST - Organ Modeling through Extraction, Representation and Understanding of Medical Image Content
4 UCL - University College of London [London]

In this work we integrate ideas from surface-based modelling with neural synthesis: we propose a combination of surface-based pose estimation and deep generative models that allows us to perform accurate pose transfer, i.e. synthesize a new image of a person based on a single image of that person and the image of a pose donor. We use a dense pose estimation system that maps pixels from both images to a common surface-based coordinate system, allowing the two images to be brought in correspondence with each other. We inpaint and refine the source image intensities in the surface coordinate system, prior to warping them onto the target pose. These predictions are fused with those of a convolutional predictive module through a neural synthesis module allowing for training the whole pipeline jointly end-to-end, optimizing a combination of adversarial and perceptual losses. We show that dense pose estimation is a substantially more powerful conditioning input than landmark- or mask-based alternatives, and report systematic improvements over state of the art generators on DeepFashion and MVC datasets. Given an input image and a target pose we use DensePose [1] to drive the generation process. This is achieved through the complementary streams of a data-driven predictive module and a surface-based module that warps the texture to UV-coordinates, interpolates on the surface and warps back to the target image. A blending module combines the complementary merits of these two streams in a single end-to-end trainable framework.

Domaines: Intelligence artificielle [cs.AI]; Vision par ordinateur et reconnaissance de formes [cs.CV]

Natalia Neverova, Riza Alp Güler, Iasonas Kokkinos. Dense Pose Transfer. European Conference on Computer Vision (ECCV) 2018, Sep 2018, Munich, Germany. ⟨hal-01951850⟩