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 41–50 of 199 papers

TitleStatusHype
Deep Dual-resolution Networks for Real-time and Accurate Semantic Segmentation of Road ScenesCode1
Boosting Night-time Scene Parsing with Learnable FrequencyCode1
PIG: Prompt Images Guidance for Night-Time Scene ParsingCode0
Complete 3D Scene Parsing from an RGBD ImageCode0
Unlocking the Full Potential of Small Data with Diverse SupervisionCode0
LF Tracy: A Unified Single-Pipeline Approach for Salient Object Detection in Light Field CamerasCode0
Improving Panoptic Segmentation for Nighttime or Low-Illumination Urban Driving ScenesCode0
PSANet: Point-wise Spatial Attention Network for Scene ParsingCode0
DeLS-3D: Deep Localization and Segmentation with a 3D Semantic MapCode0
Boosting Real-Time Driving Scene Parsing with Shared SemanticsCode0
Show:102550
← PrevPage 5 of 20Next →
All datasetsPGDP5KCityscapes test

Benchmark Results

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