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 151–160 of 199 papers

TitleStatusHype
PAD-Net: Multi-Tasks Guided Prediction-and-Distillation Network for Simultaneous Depth Estimation and Scene Parsing—0
SalientDSO: Bringing Attention to Direct Sparse OdometryCode0
Spatially Constrained Location Prior for Scene Parsing—0
Panoptic SegmentationCode1
Segmenting Sky Pixels in Images—0
Predicting Scene Parsing and Motion Dynamics in the Future—0
Complete 3D Scene Parsing from an RGBD ImageCode0
Scene Parsing with Global Context EmbeddingCode0
Scale-Adaptive Convolutions for Scene Parsing—0
Soft Correspondences in Multimodal Scene Parsing—0
Show:102550
← PrevPage 16 of 20Next →
All datasetsPGDP5KCityscapes test

Benchmark Results

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