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 101–150 of 283 papers

TitleStatusHype
Veritatem Dies Aperit- Temporally Consistent Depth Prediction Enabled by a Multi-Task Geometric and Semantic Scene Understanding ApproachCode0
Seamless Scene SegmentationCode0
Handling new target classes in semantic segmentation with domain adaptationCode0
CARL-D: A vision benchmark suite and large scale dataset for vehicle detection and scene segmentationCode0
Learning Content-enhanced Mask Transformer for Domain Generalized Urban-Scene SegmentationCode0
Learning Generalized Segmentation for Foggy-scenes by Bi-directional Wavelet GuidanceCode0
3DMV: Joint 3D-Multi-View Prediction for 3D Semantic Scene SegmentationCode0
Data Augmentation for Surgical Scene Segmentation with Anatomy-Aware Diffusion ModelsCode0
CloudAttention: Efficient Multi-Scale Attention Scheme For 3D Point Cloud LearningCode0
Real-Time Multi-Scene Visibility Enhancement for Promoting Navigational Safety of Vessels Under Complex Weather ConditionsCode0
ODFNet: Using orientation distribution functions to characterize 3D point cloudsCode0
Semantic segmentation of surgical hyperspectral images under geometric domain shiftsCode0
Relation-Aware Global Attention for Person Re-identificationCode0
Context Contrasted Feature and Gated Multi-Scale Aggregation for Scene SegmentationCode0
Self-attention on Multi-Shifted Windows for Scene SegmentationCode0
On Boosting Semantic Street Scene Segmentation with Weak SupervisionCode0
PFCNN: Convolutional Neural Networks on 3D Surfaces Using Parallel FramesCode0
Copy-Pasting Coherent Depth Regions Improves Contrastive Learning for Urban-Scene SegmentationCode0
The Utility of Decorrelating Colour Spaces in Vector Quantised Variational AutoencodersCode0
Co-Teaching for Unsupervised Domain Adaptation and ExpansionCode0
Toward Achieving Robust Low-Level and High-Level Scene ParsingCode0
One model to use them all: Training a segmentation model with complementary datasetsCode0
Towards Robust Semantic Segmentation of Accident Scenes via Multi-Source Mixed Sampling and Meta-LearningCode0
Learning Rich Features from RGB-D Images for Object Detection and SegmentationCode0
EPRNet: Efficient Pyramid Representation Network for Real-Time Street Scene SegmentationCode0
Robotic Scene Segmentation with Memory Network for Runtime Surgical Context InferenceCode0
Example-Guided Style Consistent Image Synthesis from Semantic LabelingCode0
DepthComp: real-time depth image completion based on prior semantic scene segmentationCode0
Towards Surgical Context Inference and Translation to GesturesCode0
Loci-Segmented: Improving Scene Segmentation LearningCode0
Semantic Stereo for Incidental Satellite ImagesCode0
Dirty Pixels: Towards End-to-End Image Processing and PerceptionCode0
A Benchmark for Endoluminal Scene Segmentation of Colonoscopy ImagesCode0
Self-Supervised Pre-Training Boosts Semantic Scene Segmentation on LiDAR DataCode0
Fast and Efficient: Mask Neural Fields for 3D Scene SegmentationCode0
Adversarial Style Augmentation for Domain Generalized Urban-Scene SegmentationCode0
Dual Attention Network for Scene SegmentationCode0
Index NetworkCode0
Parsing Natural Scenes and Natural Language with Recursive Neural NetworksCode0
Naive-Student: Leveraging Semi-Supervised Learning in Video Sequences for Urban Scene SegmentationCode0
Path-Invariant Map NetworksCode0
Efficient Yet Deep Convolutional Neural Networks for Semantic SegmentationCode0
End-to-end Learning of Driving Models from Large-scale Video DatasetsCode0
Tensor-Based High-Order Semantic Relation Transfer for Semantic Scene Segmentation—0
3D Learnable Supertoken Transformer for LiDAR Point Cloud Scene Segmentation—0
Unsupervised Multi-View Object Segmentation Using Radiance Field Propagation—0
PAPooling: Graph-based Position Adaptive Aggregation of Local Geometry in Point Clouds—0
PARTS: Unsupervised Segmentation With Slots, Attention and Independence Maximization—0
Pedestrian Detection aided by Deep Learning Semantic Tasks—0
Point Cloud Based Scene Segmentation: A Survey—0
Show:102550
← PrevPage 3 of 6Next →
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