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 1–25 of 199 papers

TitleStatusHype
Generalized Robot 3D Vision-Language Model with Fast Rendering and Pre-Training Vision-Language AlignmentCode3
OneFormer: One Transformer to Rule Universal Image SegmentationCode3
OCNet: Object Context Network for Scene ParsingCode2
Kimera: from SLAM to Spatial Perception with 3D Dynamic Scene GraphsCode2
Robust Shape Fitting for 3D Scene AbstractionCode2
Malleable 2.5D Convolution: Learning Receptive Fields along the Depth-axis for RGB-D Scene ParsingCode1
Global Aggregation then Local Distribution for Scene ParsingCode1
Minimal Solvers for Single-View Lens-Distorted Camera Auto-CalibrationCode1
EGFNet: Edge-Aware Guidance Fusion Network for RGB–Thermal Urban Scene ParsingCode1
Editable Free-viewpoint Video Using a Layered Neural RepresentationCode1
Mesh Convolution with Continuous Filters for 3D Surface ParsingCode1
GFF: Gated Fully Fusion for Semantic SegmentationCode1
Inter-GPS: Interpretable Geometry Problem Solving with Formal Language and Symbolic ReasoningCode1
EPSNet: Efficient Panoptic Segmentation Network with Cross-layer Attention FusionCode1
CascadePSP: Toward Class-Agnostic and Very High-Resolution Segmentation via Global and Local RefinementCode1
DPF: Learning Dense Prediction Fields with Weak SupervisionCode1
3D-to-2D Distillation for Indoor Scene ParsingCode1
Deep Dual-resolution Networks for Real-time and Accurate Semantic Segmentation of Road ScenesCode1
Strip Pooling: Rethinking Spatial Pooling for Scene ParsingCode1
Boosting Night-time Scene Parsing with Learnable FrequencyCode1
A Dense Material Segmentation Dataset for Indoor and Outdoor Scene ParsingCode1
BORM: Bayesian Object Relation Model for Indoor Scene RecognitionCode1
Fast and Accurate Scene Parsing via Bi-direction Alignment NetworksCode1
AttaNet: Attention-Augmented Network for Fast and Accurate Scene ParsingCode1
Context-Aware Synthesis and Placement of Object InstancesCode1
Show:102550
← PrevPage 1 of 8Next →
All datasetsPGDP5KCityscapes test

Benchmark Results

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