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 71–80 of 199 papers

TitleStatusHype
Editable Free-viewpoint Video Using a Layered Neural RepresentationCode1
3D-to-2D Distillation for Indoor Scene ParsingCode1
Evidential fully convolutional network for semantic segmentationCode1
AttaNet: Attention-Augmented Network for Fast and Accurate Scene ParsingCode1
Perception Framework through Real-Time Semantic Segmentation and Scene Recognition on a Wearable System for the Visually Impaired—0
SOSD-Net: Joint Semantic Object Segmentation and Depth Estimation from Monocular images—0
Kimera: from SLAM to Spatial Perception with 3D Dynamic Scene GraphsCode2
Deep Dual-resolution Networks for Real-time and Accurate Semantic Segmentation of Road ScenesCode1
ORDNet: Capturing Omni-Range Dependencies for Scene Parsing—0
An Evolution of CNN Object Classifiers on Low-Resolution Images—0
Show:102550
← PrevPage 8 of 20Next →
All datasetsPGDP5KCityscapes test

Benchmark Results

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