SOTAVerified

Scene Segmentation

Scene segmentation is the task of splitting a scene into its various object components.

Image adapted from Temporally coherent 4D reconstruction of complex dynamic scenes.

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 101–125 of 283 papers

TitleStatusHype
Paced-Curriculum Distillation with Prediction and Label Uncertainty for Image SegmentationCode1
Attention Discriminant Sampling for Point Clouds—0
Uni-3D: A Universal Model for Panoptic 3D Scene ReconstructionCode1
AttEntropy: On the Generalization Ability of Supervised Semantic Segmentation Transformers to New Objects in New DomainsCode0
Efficient Movie Scene Detection using State-Space TransformersCode1
Push-the-Boundary: Boundary-aware Feature Propagation for Semantic Segmentation of 3D Point CloudsCode1
Urban Scene Semantic Segmentation with Low-Cost Coarse Annotation—0
Tencent AVS: A Holistic Ads Video Dataset for Multi-modal Scene Segmentation—0
CONDA: Continual Unsupervised Domain Adaptation Learning in Visual Perception for Self-Driving Cars—0
Residual Pattern Learning for Pixel-wise Out-of-Distribution Detection in Semantic SegmentationCode1
Copy-Pasting Coherent Depth Regions Improves Contrastive Learning for Urban-Scene SegmentationCode0
Autonomous Marker-less Rapid Aerial Grasping—0
Improving Pixel-Level Contrastive Learning by Leveraging Exogenous Depth Information—0
Quantifying Model Uncertainty for Semantic Segmentation using Operators in the RKHS—0
Transformer-based Flood Scene Segmentation for Developing Countries—0
Unsupervised RGB-to-Thermal Domain Adaptation via Multi-Domain Attention NetworkCode1
Point Cloud Recognition with Position-to-Structure Attention Transformers—0
Unsupervised Multi-View Object Segmentation Using Radiance Field Propagation—0
Diffusion Unit: Interpretable Edge Enhancement and Suppression Learning for 3D Point Cloud SegmentationCode1
Active Self-Training for Weakly Supervised 3D Scene Semantic Segmentation—0
Introducing Intermediate Domains for Effective Self-Training during Test-TimeCode0
CloudAttention: Efficient Multi-Scale Attention Scheme For 3D Point Cloud LearningCode0
Pseudo-label Guided Cross-video Pixel Contrast for Robotic Surgical Scene Segmentation with Limited Annotations—0
Adversarial Style Augmentation for Domain Generalized Urban-Scene SegmentationCode0
Self-attention on Multi-Shifted Windows for Scene SegmentationCode0
Show:102550
← PrevPage 5 of 12Next →
All datasetsSUN-RGBDScanNetStreetHazardsMovieNetUAVid

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1ICMMean IoU50.6—Unverified
2Index NetworkMean IoU33.48—Unverified
3DeepLab-LargeFOVMean IoU32.08—Unverified
4SegNetMean IoU31.84—Unverified
5FCNMean IoU27.39—Unverified
#ModelMetricClaimedVerifiedStatus
13DMVAverage Accuracy75—Unverified
2KPConv3DIoU68.6—Unverified
3PointNet++Average Accuracy60.2—Unverified
#ModelMetricClaimedVerifiedStatus
1Mask2AnomalyOpen-mIoU59.8—Unverified
2LDN121-RPLOpen-mIoU56.3—Unverified
3LDN121-DenseHybridOpen-mIoU45.8—Unverified
#ModelMetricClaimedVerifiedStatus
1NeighborNetAP71.9—Unverified
2TranS4merAP60.78—Unverified
#ModelMetricClaimedVerifiedStatus
1UNetFormerCategory mIoU67.8—Unverified