BMIPL’s paper accepted to CVPR 2019
One BMIPL’s paper, “Training deep learning based image denoisers from undersampled measurements without ground truth and without image prior,” by Magauiya Zhussip, Shakarim Soltanayev and Se Young Chun has been accepted to CVPR 2019 (acceptance rate: 25.2%). Magauiya Zhussip and Shakarim Soltanayev are both second year MS students at BMIPL. CVPR is one of the top computer vision conferences. Last year, there have been a few works on training deep learning based denoisers without ground truth by NVIDIA (noise2noise) and BMIPL@UNIST (SURE based training). We extended our previous work to unsupervised learning of image denoisers in (undersampled) compressive sensing (CS) domain.