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 31–40 of 199 papers

TitleStatusHype
Deep Dual-resolution Networks for Real-time and Accurate Semantic Segmentation of Road ScenesCode1
Editable Free-viewpoint Video Using a Layered Neural RepresentationCode1
3D-to-2D Distillation for Indoor Scene ParsingCode1
DPF: Learning Dense Prediction Fields with Weak SupervisionCode1
EGFNet: Edge-Aware Guidance Fusion Network for RGB–Thermal Urban Scene ParsingCode1
EPSNet: Efficient Panoptic Segmentation Network with Cross-layer Attention FusionCode1
Fast and Accurate Scene Parsing via Bi-direction Alignment NetworksCode1
Global Aggregation then Local Distribution for Scene ParsingCode1
Multi-Grained Contrast for Data-Efficient Unsupervised Representation LearningCode1
Traffic Scene Parsing through the TSP6K DatasetCode1
Show:102550
← PrevPage 4 of 20Next →
All datasetsPGDP5KCityscapes test

Benchmark Results

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