Physics-informed Guided Disentanglement in Generative Networks - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Journal Articles IEEE Transactions on Pattern Analysis and Machine Intelligence Year : 2023

Physics-informed Guided Disentanglement in Generative Networks

Abstract

Image-to-image translation (i2i) networks suffer from entanglement effects in presence of physics-related phenomena in target domain (such as occlusions, fog, etc), thus lowering the translation quality and variability. In this paper, we present a comprehensive method for disentangling physics-based traits in the translation, guiding the learning process with neural or physical models. For the latter, we integrate adversarial estimation and genetic algorithms to correctly achieve disentanglement. The results show our approach dramatically increase performances in many challenging scenarios for image translation.

Dates and versions

hal-03498130 , version 1 (20-12-2021)

Licence

Identifiers

Cite

Fabio Pizzati, Pietro Cerri, Raoul de Charette. Physics-informed Guided Disentanglement in Generative Networks. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2023, ⟨10.1109/tpami.2023.3257486⟩. ⟨hal-03498130⟩

Collections

INRIA INRIA2 ANR
40 View
0 Download

Altmetric

Share

Gmail Mastodon Facebook X LinkedIn More