Image Reconstruction using Superpixel Clustering and Tensor Completion
This is an incremental improvement for image compression and reconstruction tasks.
The paper tackles image reconstruction from sparse samples by selecting representative pixels from superpixel regions and using tensor completion, achieving better results than uniform sampling across various missing ratios.
This paper presents a pixel selection method for compact image representation based on superpixel segmentation and tensor completion. Our method divides the image into several regions that capture important textures or semantics and selects a representative pixel from each region to store. We experiment with different criteria for choosing the representative pixel and find that the centroid pixel performs the best. We also propose two smooth tensor completion algorithms that can effectively reconstruct different types of images from the selected pixels. Our experiments show that our superpixel-based method achieves better results than uniform sampling for various missing ratios.