Model-based occlusion disentanglement for image-to-image translation - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Conference Papers Year : 2020

Model-based occlusion disentanglement for image-to-image translation

Abstract

Image-to-image translation is affected by entanglement phenomena, which may occur in case of target data encompassing occlusions such as raindrops, dirt, etc. Our unsupervised model-based learning disentangles scene and occlusions, while benefiting from an adversarial pipeline to regress physical parameters of the occlusion model. The experiments demonstrate our method is able to handle varying types of occlusions and generate highly realistic translations, qualitatively and quantitatively outperforming the state-of-the-art on multiple datasets.

Dates and versions

hal-02947036 , version 1 (23-09-2020)

Identifiers

Cite

Fabio Pizzati, Pietro Cerri, Raoul de Charette. Model-based occlusion disentanglement for image-to-image translation. ECCV 2020 - European Conference on Computer Vision, Aug 2020, Glasgow / Virtual, United Kingdom. ⟨hal-02947036⟩

Collections

INRIA INRIA2
75 View
0 Download

Altmetric

Share

Gmail Mastodon Facebook X LinkedIn More