DerainNeRF: 3D Scene Estimation with Adhesive Waterdrop Removal

arXiv:2403.20013v1 Announce Type: new
Abstract: When capturing images through the glass during rainy or snowy weather conditions, the resulting images often contain waterdrops adhered on the glass surface, and these waterdrops significantly degrade the image quality and performance of many computer vision algorithms. To tackle these limitations, we propose a method to reconstruct the clear 3D scene implicitly from multi-view images degraded by waterdrops. Our method exploits an attention network to predict the location of waterdrops and then train a …

abstract algorithms arxiv computer computer vision cs.cv glass image images limitations performance quality surface through type vision weather