SOTAVerified

Scene Parsing

Scene parsing is to segment and parse an image into different image regions associated with semantic categories, such as sky, road, person, and bed. MIT Description

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 111–120 of 199 papers

TitleStatusHype
Boosting Real-Time Driving Scene Parsing with Shared SemanticsCode0
Holistic++ Scene Understanding: Single-view 3D Holistic Scene Parsing and Human Pose Estimation with Human-Object Interaction and Physical Commonsense—0
SPGNet: Semantic Prediction Guidance for Scene Parsing—0
Consensus Feature Network for Scene Parsing—0
Quadtree Generating Networks: Efficient Hierarchical Scene Parsing with Sparse ConvolutionsCode0
Context-Integrated and Feature-Refined Network for Lightweight Object Parsing—0
SlimYOLOv3: Narrower, Faster and Better for Real-Time UAV ApplicationsCode0
ELKPPNet: An Edge-aware Neural Network with Large Kernel Pyramid Pooling for Learning Discriminative Features in Semantic Segmentation—0
Active Scene Understanding via Online Semantic Reconstruction—0
Oceanic Eddy Identification Using an AI Scheme—0
Show:102550
← PrevPage 12 of 20Next →
All datasetsPGDP5KCityscapes test

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1PGDPNetTotal Accuracy84.7—Unverified
2Inter-GPSTotal Accuracy27.3—Unverified
#ModelMetricClaimedVerifiedStatus
1VCD No CoarsemIoU82.3—Unverified