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 151–175 of 371 papers

TitleStatusHype
Fast and Accurate Depth Estimation from Sparse Light Fields—0
Extract and Merge: Superpixel Segmentation with Regional Attributes—0
Closed-Loop Adaptation for Weakly-Supervised Semantic Segmentation—0
An Explainable Deep Learning-Based Method For Schizophrenia Diagnosis Using Generative Data-Augmentation—0
Adaptive strategy for superpixel-based region-growing image segmentation—0
A Bottom-Up Approach for Automatic Pancreas Segmentation in Abdominal CT Scans—0
Exposure Fusion for Hand-held Camera Inputs with Optical Flow and PatchMatch—0
Explaining Deep Neural Networks—0
Classifier Based Graph Construction for Video Segmentation—0
Cascaded Scene Flow Prediction using Semantic Segmentation—0
Egocentric Hand Detection Via Dynamic Region Growing—0
Capturing global spatial context for accurate cell classification in skin cancer histology—0
Efficient Graph Cut Optimization for Full CRFs with Quantized Edges—0
Efficient Classifier Training to Minimize False Merges in Electron Microscopy Segmentation—0
Boosting Convolutional Features for Robust Object Proposals—0
AlphaTablets: A Generic Plane Representation for 3D Planar Reconstruction from Monocular Videos—0
Localized Perturbations For Weakly-Supervised Segmentation of Glioma Brain Tumours—0
LIBSVX: A Supervoxel Library and Benchmark for Early Video Processing—0
Leveraging Activations for Superpixel Explanations—0
Efficient 3D Room Shape Recovery From a Single Panorama—0
Left/Right Hand Segmentation in Egocentric Videos—0
Leave-One-Out Kernel Optimization for Shadow Detection—0
Dynamic Spectral Residual Superpixels—0
A Weighted Sparse Coding Framework for Saliency Detection—0
Learning to Segment Human by Watching YouTube—0
Show:102550
← PrevPage 7 of 15Next →

No leaderboard results yet.