Adding 2,000 CycleGAN-generated synthetic nighttime images to 5,000 real daytime BDD images lifts nighttime semantic segmentation mean IoU from 32.72% to 43.14% on the BDD night validation set.
I Can See Clearly Now : Image Restoration via De-Raining
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
abstract
We present a method for improving segmentation tasks on images affected by adherent rain drops and streaks. We introduce a novel stereo dataset recorded using a system that allows one lens to be affected by real water droplets while keeping the other lens clear. We train a denoising generator using this dataset and show that it is effective at removing the effect of real water droplets, in the context of image reconstruction and road marking segmentation. To further test our de-noising approach, we describe a method of adding computer-generated adherent water droplets and streaks to any images, and use this technique as a proxy to demonstrate the effectiveness of our model in the context of general semantic segmentation. We benchmark our results using the CamVid road marking segmentation dataset, Cityscapes semantic segmentation datasets and our own real-rain dataset, and show significant improvement on all tasks.
fields
cs.CV 1years
2019 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
See Clearer at Night: Towards Robust Nighttime Semantic Segmentation through Day-Night Image Conversion
Adding 2,000 CycleGAN-generated synthetic nighttime images to 5,000 real daytime BDD images lifts nighttime semantic segmentation mean IoU from 32.72% to 43.14% on the BDD night validation set.