SOTAVerified

Superpixels

Superpixel techniques segment an image into regions based on similarity measures that utilize perceptual features, effectively grouping pixels that appear similar. The motivation behind this approach is to generate regions that provide meaningful descriptions while significantly reducing the data volume compared to using every individual pixel. By decreasing the number of primitives, these techniques reduce redundancy and simplify the complexity of recognition tasks. Superpixels replace the rigid structure of individual pixels with delineated regions that preserve meaningful content in the image, thereby aiding the interpretation of the scene’s structure and simplifying subsequent processing tasks. Generally, superpixel techniques rely on measures that evaluate color similarities and the shapes of regions, incorporating edges or significant changes in intensity to define these regions.

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 126–150 of 371 papers

TitleStatusHype
UniDAformer: Unified Domain Adaptive Panoptic Segmentation Transformer via Hierarchical Mask Calibration—0
Dense semantic labeling of sub-decimeter resolution images with convolutional neural networks—0
Delving Deep into Semantic Relation Distillation—0
Automatic segmentation of trees in dynamic outdoor environments—0
Deep Superpixel Cut for Unsupervised Image Segmentation—0
Automatic 3D Indoor Scene Modeling From Single Panorama—0
GASP, a generalized framework for agglomerative clustering of signed graphs and its application to Instance Segmentation—0
Lazy Random Walks for Superpixel Segmentation—0
Automated Linear-Time Detection and Quality Assessment of Superpixels in Uncalibrated True- or False-Color RGB Images—0
Automated Vision-based Bridge Component Extraction Using Multiscale Convolutional Neural Networks—0
Lagrangian Motion Fields for Long-term Motion Generation—0
Deep Green Function Convolution for Improving Saliency in Convolutional Neural Networks—0
DeepFH Segmentations for Superpixel-based Object Proposal Refinement—0
A Bottom-up Approach for Pancreas Segmentation using Cascaded Superpixels and (Deep) Image Patch Labeling—0
LargeAD: Large-Scale Cross-Sensor Data Pretraining for Autonomous Driving—0
Learning from multiscale wavelet superpixels using GNN with spatially heterogeneous pooling—0
Image segmentation with superpixel-based covariance descriptors in low-rank representation—0
Deep Deconvolutional Networks for Scene Parsing—0
Iterative, Deep, and Unsupervised Synthetic Aperture Sonar Image Segmentation—0
Deep convolutional networks for pancreas segmentation in CT imaging—0
Improved Image Boundaries for Better Video Segmentation—0
Improving an Object Detector and Extracting Regions Using Superpixels—0
Improving Scene Graph Generation with Superpixel-Based Interaction Learning—0
DeepOrgan: Multi-level Deep Convolutional Networks for Automated Pancreas Segmentation—0
Image Segmentation Based on Multiscale Fast Spectral Clustering—0
Show:102550
← PrevPage 6 of 15Next →

No leaderboard results yet.