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 11–20 of 199 papers

TitleStatusHype
EPSNet: Efficient Panoptic Segmentation Network with Cross-layer Attention FusionCode1
Context-Aware Synthesis and Placement of Object InstancesCode1
Deep Dual-resolution Networks for Real-time and Accurate Semantic Segmentation of Road ScenesCode1
DPF: Learning Dense Prediction Fields with Weak SupervisionCode1
CascadePSP: Toward Class-Agnostic and Very High-Resolution Segmentation via Global and Local RefinementCode1
Editable Free-viewpoint Video Using a Layered Neural RepresentationCode1
3D-to-2D Distillation for Indoor Scene ParsingCode1
Edge-aware Guidance Fusion Network for RGB Thermal Scene ParsingCode1
Strip Pooling: Rethinking Spatial Pooling for Scene ParsingCode1
AttaNet: Attention-Augmented Network for Fast and Accurate Scene ParsingCode1
Show:102550
← PrevPage 2 of 20Next →
All datasetsPGDP5KCityscapes test

Benchmark Results

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