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

Showing 51100 of 283 papers

TitleStatusHype
Context Prior for Scene SegmentationCode1
A Shared Representation for Photorealistic Driving SimulatorsCode1
FIFO: Learning Fog-invariant Features for Foggy Scene SegmentationCode1
Query3D: LLM-Powered Open-Vocabulary Scene Segmentation with Language Embedded 3D GaussianCode1
Rethinking Surgical Instrument Segmentation: A Background Image Can Be All You NeedCode1
MammAlps: A multi-view video behavior monitoring dataset of wild mammals in the Swiss AlpsCode1
Panoptic SegmentationCode1
CD-COCO: A Versatile Complex Distorted COCO Database for Scene-Context-Aware Computer VisionCode1
PointNet: Deep Learning on Point Sets for 3D Classification and SegmentationCode1
Point TransformerCode1
FTNet: Feature Transverse Network for Thermal Image Semantic SegmentationCode1
Push-the-Boundary: Boundary-aware Feature Propagation for Semantic Segmentation of 3D Point CloudsCode1
Adaptive Boosting for Domain Adaptation: Towards Robust Predictions in Scene SegmentationCode1
Test-time Adaptation with Slot-Centric ModelsCode1
DenseHybrid: Hybrid Anomaly Detection for Dense Open-set RecognitionCode1
2018 Robotic Scene Segmentation ChallengeCode1
A Local-to-Global Approach to Multi-modal Movie Scene SegmentationCode1
Fusion-Aware Point Convolution for Online Semantic 3D Scene SegmentationCode1
IBISCape: A Simulated Benchmark for multi-modal SLAM Systems Evaluation in Large-scale Dynamic EnvironmentsCode1
Double Domain Guided Real-Time Low-Light Image Enhancement for Ultra-High-Definition Transportation SurveillanceCode1
BitQ: Tailoring Block Floating Point Precision for Improved DNN Efficiency on Resource-Constrained DevicesCode1
DSPoint: Dual-scale Point Cloud Recognition with High-frequency FusionCode1
AdaptiveSAM: Towards Efficient Tuning of SAM for Surgical Scene SegmentationCode1
DualConvMesh-Net: Joint Geodesic and Euclidean Convolutions on 3D MeshesCode1
GNeSF: Generalizable Neural Semantic FieldsCode1
ROAD-Waymo: Action Awareness at Scale for Autonomous DrivingCode1
Efficient Movie Scene Detection using State-Space TransformersCode1
Boundary-aware Self-supervised Learning for Video Scene SegmentationCode1
Self-positioning Point-based Transformer for Point Cloud UnderstandingCode1
Learning and Reasoning with the Graph Structure Representation in Robotic SurgeryCode1
PS^2-Net: A Locally and Globally Aware Network for Point-Based Semantic SegmentationCode0
Point-Voxel CNN for Efficient 3D Deep LearningCode0
Real-Time Multi-Scene Visibility Enhancement for Promoting Navigational Safety of Vessels Under Complex Weather ConditionsCode0
Parsing Natural Scenes and Natural Language with Recursive Neural NetworksCode0
Path-Invariant Map NetworksCode0
Co-Teaching for Unsupervised Domain Adaptation and ExpansionCode0
AttEntropy: On the Generalization Ability of Supervised Semantic Segmentation Transformers to New Objects in New DomainsCode0
PDFNet: Pointwise Dense Flow Network for Urban-Scene SegmentationCode0
Relation-Aware Global Attention for Person Re-identificationCode0
Copy-Pasting Coherent Depth Regions Improves Contrastive Learning for Urban-Scene SegmentationCode0
PFCNN: Convolutional Neural Networks on 3D Surfaces Using Parallel FramesCode0
Adversarial Style Augmentation for Domain Generalized Urban-Scene SegmentationCode0
On Boosting Semantic Street Scene Segmentation with Weak SupervisionCode0
One model to use them all: Training a segmentation model with complementary datasetsCode0
Context Contrasted Feature and Gated Multi-Scale Aggregation for Scene SegmentationCode0
FREDOM: Fairness Domain Adaptation Approach to Semantic Scene UnderstandingCode0
A Benchmark for Endoluminal Scene Segmentation of Colonoscopy ImagesCode0
ODFNet: Using orientation distribution functions to characterize 3D point cloudsCode0
Learning Rich Features from RGB-D Images for Object Detection and SegmentationCode0
CloudAttention: Efficient Multi-Scale Attention Scheme For 3D Point Cloud LearningCode0
Show:102550
← PrevPage 2 of 6Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1ICMMean IoU50.6Unverified
2Index NetworkMean IoU33.48Unverified
3DeepLab-LargeFOVMean IoU32.08Unverified
4SegNetMean IoU31.84Unverified
5FCNMean IoU27.39Unverified
#ModelMetricClaimedVerifiedStatus
13DMVAverage Accuracy75Unverified
2KPConv3DIoU68.6Unverified
3PointNet++Average Accuracy60.2Unverified
#ModelMetricClaimedVerifiedStatus
1Mask2AnomalyOpen-mIoU59.8Unverified
2LDN121-RPLOpen-mIoU56.3Unverified
3LDN121-DenseHybridOpen-mIoU45.8Unverified
#ModelMetricClaimedVerifiedStatus
1NeighborNetAP71.9Unverified
2TranS4merAP60.78Unverified
#ModelMetricClaimedVerifiedStatus
1UNetFormerCategory mIoU67.8Unverified