Skip to Main content Skip to Navigation
Conference papers

Physics-Based Rendering for Improving Robustness to Rain

Abstract : To improve the robustness to rain, we present a physically-based rain rendering pipeline for realistically inserting rain into clear weather images. Our rendering relies on a physical particle simulator, an estimation of the scene lighting and an accurate rain photometric modeling to augment images with arbitrary amount of realistic rain or fog. We validate our rendering with a user study, proving our rain is judged 40% more realistic that state-of-the-art. Using our generated weather augmented Kitti and Cityscapes dataset, we conduct a thorough evaluation of deep object detection and semantic segmentation algorithms and show that their performance decreases in degraded weather, on the order of 15% for object detection and 60% for semantic segmentation. Furthermore, we show refining existing networks with our augmented images improves the robustness of both object detection and semantic segmentation algorithms. We experiment on nuScenes and measure an improvement of 15% for object detection and 35% for semantic segmentation compared to original rainy performance. Augmented databases and code are available on the project page.
Document type :
Conference papers
Complete list of metadata

https://hal.inria.fr/hal-02385436
Contributor : Raoul de Charette <>
Submitted on : Thursday, November 28, 2019 - 6:00:51 PM
Last modification on : Monday, July 20, 2020 - 1:06:06 PM

Links full text

Identifiers

  • HAL Id : hal-02385436, version 1
  • ARXIV : 1908.10335

Collections

Citation

Shirsendu Sukanta Halder, Jean-François Lalonde, Raoul de Charette. Physics-Based Rendering for Improving Robustness to Rain. ICCV 2019 - International Conference on Computer Vision, Oct 2019, Seoul, South Korea. ⟨hal-02385436⟩

Share

Metrics

Record views

152