Multi-Domain Conditional Image Translation: Translating Driving Datasets from Clear-Weather to Adverse Conditions

Vinod, V and Ram Prabhakar, K and Venkatesh Babu, R and Chakraborty, A (2021) Multi-Domain Conditional Image Translation: Translating Driving Datasets from Clear-Weather to Adverse Conditions. In: 18th IEEE/CVF International Conference on Computer Vision Workshops, ICCVW 2021, 11-17 Oct 2021, Virtual, Online, pp. 1571-1582.

PDF Multi-Domain_Conditional_Image_Translation_Translating_Driving_Datasets_from_Clear-Weather_to_Adverse_Conditions.pdf - Published Version Restricted to Registered users only Download (2MB) | Request a copy

Abstract

Vision systems for fully autonomous navigation must perform well even in unstructured and degraded scenarios. In most driving datasets today, there is a bias toward clear-weather conditions as compared with extreme-weather owing to the difficulty in capturing and annotating large-scale image datasets degraded by adverse weather. While there has been extensive research on techniques such as deraining, dehazing and on tasks such as segmentation and domain adaptation, there has been minimal attention toward methods to effectively translate clear-weather driving datasets to extreme-weather domains. To address this, we present a method that builds on recent advances in Generative Networks and Self-Supervised Learning to perform conditional multi-domain image translation. We evaluate our method on the semantic scene understanding task and demonstrate quantitatively superior translation results from clear-weather conditions to adverse-weather shifted domains such as Rain, Night and Fog conditions. From our experiments, we show improved domain invariant content disentanglement, and segmentation methods trained with datasets translated using the proposed method have improved performance over single and multi-domain image translation baselines on real-world adverse weather data. © 2021 IEEE.

Item Type:	Conference Paper
Publication:	Proceedings of the IEEE International Conference on Computer Vision
Publisher:	Institute of Electrical and Electronics Engineers Inc.
Additional Information:	The copyright for this article belongs to Institute of Electrical and Electronics Engineers Inc.
Keywords:	Computer vision; Demulsification; Image enhancement; Image segmentation; Meteorology; Semantics, Adverse weather; Autonomous navigation; Condition; Dehazing; Domain adaptation; Extreme weather; Image translation; Large-scale image datasets; Multi-domains; Vision systems, Large dataset
Department/Centre:	Division of Interdisciplinary Sciences > Computational and Data Sciences
Date Deposited:	01 Feb 2022 12:36
Last Modified:	01 Feb 2022 12:36
URI:	http://eprints.iisc.ac.in/id/eprint/71200

Actions (login required)

View Item