paper-with-me

Papers

Image Reconstruction using Superpixel Clustering and Tensor Completion

2023-05-16 · Maame G. Asante-Mensah, Anh Huy Phan, Salman Ahmadi-Asl, Zaher Al Aghbari, Andrzej Cichocki

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.

📄 PDF Abstract BibTeX arXiv:2305.09564

Code (0)

등록된 구현이 없습니다.

Tasks

ClusteringImage Reconstruction

Similar Papers 제목 키워드 기반

Beyond Low Rank: A Graph-Based Propagation Approach to Tensor Completion for Multi-Acquisition Scenarios

2023-12-06 · Iain Rolland, Sivasakthy Selvakumaran, Andrea Marinoni

Tensor completion refers to the problem of recovering the missing, corrupted or unobserved entries in data represented by tensors. In this paper, we tackle the tensor completion problem in the scenario in which multiple …

A novel centroid update approach for clustering-based superpixel methods and superpixel-based edge detection

2019-10-18 · Houwang Zhang, Chong Wu, Le Zhang, Hanying Zheng

Superpixel is widely used in image processing. And among the methods for superpixel generation, clustering-based methods have a high speed and a good performance at the same time. However, most clustering-based superpixe…

ClusteringEdge Detection

Pixel-Level Clustering Network for Unsupervised Image Segmentation

2023-10-24 · Cuong Manh Hoang, Byeongkeun Kang

While image segmentation is crucial in various computer vision applications, such as autonomous driving, grasping, and robot navigation, annotating all objects at the pixel-level for training is nearly impossible. Theref…

Autonomous DrivingClusteringImage ReconstructionImage Segmentation+6

Joint Superpixel and Self-Representation Learning for Scalable Hyperspectral Image Clustering

2025-09-28 · Xianlu Li, Nicolas Nadisic, Shaoguang Huang, Aleksandra Pizurica arxiv

Subspace clustering is a powerful unsupervised approach for hyperspectral image (HSI) analysis, but its high computational and memory costs limit scalability. Superpixel segmentation can improve efficiency by reducing th…

Representation LearningImage Clustering

Tensor Alignment Based Domain Adaptation for Hyperspectral Image Classification

2018-08-29 · Yao Qin, Lorenzo Bruzzone, Biao Li

This paper presents a tensor alignment (TA) based domain adaptation method for hyperspectral image (HSI) classification. To be specific, HSIs in both domains are first segmented into superpixels and tensors of both domai…

ClassificationDomain AdaptationGeneral ClassificationHyperspectral Image Classification+3