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 171–180 of 199 papers

TitleStatusHype
Improving Panoptic Segmentation for Nighttime or Low-Illumination Urban Driving ScenesCode0
Auto-Retoucher(ART) - A framework for Background Replacement and Image EditingCode0
PIG: Prompt Images Guidance for Night-Time Scene ParsingCode0
Holistic 3D Scene Parsing and Reconstruction from a Single RGB ImageCode0
HAPNet: Toward Superior RGB-Thermal Scene Parsing via Hybrid, Asymmetric, and Progressive Heterogeneous Feature FusionCode0
What's There in the DarkCode0
PSANet: Point-wise Spatial Attention Network for Scene ParsingCode0
FLOAT: Factorized Learning of Object Attributes for Improved Multi-object Multi-part Scene ParsingCode0
Few-Shot Fruit Segmentation via Transfer LearningCode0
Quadtree Generating Networks: Efficient Hierarchical Scene Parsing with Sparse ConvolutionsCode0
Show:102550
← PrevPage 18 of 20Next →
All datasetsPGDP5KCityscapes test

Benchmark Results

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