A multiscale model for rain rendering in real-time

Weber, Yoann; Jolivet, Vincent; Gilet, Guillaume; Ghazanfarpour, Djamchid

doi:10.1016/j.cag.2015.04.007

Cited by 14 publications

(6 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In particular, they propose an image-based rain streak database [20] modeling the drop oscillations, which we exploit in our physics-based rendering framework. Other streak appearance models were proposed in [71,3] using a frequency model. Realistic rendering was also obtained with ray-tracing [64] or artistic-based techniques [69,14] but on synthetic data as they require complete 3D knowledge of the scene including accurate light estimation.…”

Section: Rain Modelingmentioning

confidence: 99%

“…In practice, most drops in a rainfall are actually imaged as fog-like rain 1 , though their visual effect is less dominant. We render the volumetric attenuation using the model described in [71] where the per-pixel attenuation I att is expressed as the sum of the extinction L ext caused by the volume of rain and the airlight scattering A in that results of the environmental lighting. Using equations from [71] to model the attenuation image at pixel x we get…”

Section: Fog-like Rainmentioning

confidence: 99%

See 1 more Smart Citation

Rain rendering for evaluating and improving robustness to bad weather

Tremblay,

Halder,

de Charette

et al. 2020

Preprint

View full text Add to dashboard Cite

Rain fills the atmosphere with water particles, which breaks the common assumption that light travels unaltered from the scene to the camera. While it is well-known that rain affects computer vision algorithms, quantifying its impact is difficult. In this context, we present a rain rendering pipeline that enables the systematic evaluation of common computer vision algorithms to controlled amounts of rain. We present three different ways to add synthetic rain to existing images datasets: completely physic-based; completely data-driven; and a combination of both. The physic-based rain augmentation combines a physical particle simulator and accurate rain photometric modeling. We validate our rendering methods with a user study, demonstrating our rain is judged as much as 73% more realistic than the state-of-theart. Using our generated rain-augmented KITTI, Cityscapes, and nuScenes datasets, we conduct a thorough evaluation of object detection, semantic segmentation, and depth estimation algorithms and show that their performance decreases in degraded weather, on the order of 15% for object detection, 60% for semantic segmentation, and 6-fold increase in depth estimation error. Finetuning on our augmented synthetic data results in improvements of 21% on object detection, 37% on semantic segmentation, and 8% on depth estimation. Keywords Adverse weather • vision and rain • physicsbased rendering • image to image translation • GAN

show abstract

Section: Rain Modelingmentioning

confidence: 99%

Section: Fog-like Rainmentioning

confidence: 99%

Rain rendering for evaluating and improving robustness to bad weather

Tremblay,

Halder,

de Charette

et al. 2020

Preprint

View full text Add to dashboard Cite

show abstract

“…In particular, they propose an image-based rain streak database [16] modeling the drop oscillations, which we exploit in our rendering framework. Other streak appearance models were proposed in [51,2] using a frequency model. Realistic rendering was also obtained with ray-tracing [44] or artistic-based techniques [48,9] but on synthetic data as they requires complete 3D knowledge of the scene including accurate light estimation.…”

Section: Related Workmentioning

confidence: 99%

“…We render volumetric attenuation using the model described in [51] where the per-pixel attenuation I att is expressed as the sum of the extinction L ext caused by the volume of rain and the airlight scattering A in that results of the environmental lighting. Using equations from [51] to model the attenuation image at pixel x we obtain…”

Section: Fog-like Rainmentioning

confidence: 99%

Physics-Based Rendering for Improving Robustness to Rain

Lalonde¹,

Charette²

2019

Preprint

View full text Add to dashboard Cite

To improve the robustness to rain, we present a physicallybased 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.

show abstract

“…For example, a rainy scene is typically composed of many raindrops -each with a size much larger than visible wave lengths, which causes the light to spread in a specific way. Closer raindrops, which have a projected size larger than a pixel, are individually visible, and further ones can only be seen in a macroscopic view as participating media [14]. Weather scenes include several effects such as streaks due to the velocity of raindrops and camera's exposure time, individual snow or rain particles and visibility is decreasing until details blur into a fog like appearance.…”

Section: Weather Conditionsmentioning

confidence: 99%

Dynamic texture recognition under adverse lighting and weather conditions for outdoor environments

Pyataeva

2019

E3S Web Conf.

View full text Add to dashboard Cite

Recognizing dynamic patterns based on visual processing is significant for many applications. In this paper dynamic texture recognition focuses on outdoor scenarios where a crisis event might occur (i.e. fire in a forest, floods/flooding etc.) Real outdoor scenes may include the objects with dynamic behaviour due to illumination, blurring, or weather conditions effects. Under bad weather conditions the imaging systems is degraded and produce low visibility images. In this work precipitation artefacts and lightning effects for dynamic texture analysis were studied. Experimental results show that the proposed method of weather and adverse lighting effects compensation is feasible and effective for videobased dynamic texture analysis under bad weather conditions.

show abstract

A multiscale model for rain rendering in real-time

Cited by 14 publications

References 18 publications

Rain rendering for evaluating and improving robustness to bad weather

Rain rendering for evaluating and improving robustness to bad weather

Physics-Based Rendering for Improving Robustness to Rain

Dynamic texture recognition under adverse lighting and weather conditions for outdoor environments

Contact Info

Product

Resources

About