The traditional image Compressive Sensing (CS) conducts block-wise sampling with the same sampling rate. However, some\nblocking artifacts often occur due to the varying block sparsity, leading to a low rate-distortion performance. To suppress these\nblocking artifacts, we propose to adaptively sample each block according to texture features in this paper. With the maximum\ngradient in 8-connected region of each pixel, we measure the texture variation of each pixel and then compute the texture contrast\nof each block. According to the distribution of texture contrast, we adaptively set the sampling rate of each block and finally build\nan image reconstruction model using these block texture contrasts. Experimental results show that our adaptive sampling scheme\nimproves the rate-distortion performance of image CS compared with the existing adaptive schemes and the reconstructed images\nby our method achieve better visual quality.
Loading....