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

Showing 110 of 199 papers

TitleStatusHype
OneFormer: One Transformer to Rule Universal Image SegmentationCode3
Generalized Robot 3D Vision-Language Model with Fast Rendering and Pre-Training Vision-Language AlignmentCode3
Kimera: from SLAM to Spatial Perception with 3D Dynamic Scene GraphsCode2
Robust Shape Fitting for 3D Scene AbstractionCode2
OCNet: Object Context Network for Scene ParsingCode2
Context-Aware Synthesis and Placement of Object InstancesCode1
Boosting Night-time Scene Parsing with Learnable FrequencyCode1
Deep Dual-resolution Networks for Real-time and Accurate Semantic Segmentation of Road ScenesCode1
Strip Pooling: Rethinking Spatial Pooling for Scene ParsingCode1
BORM: Bayesian Object Relation Model for Indoor Scene RecognitionCode1
Show:102550
← PrevPage 1 of 20Next →

Benchmark Results

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