SOTAVerified

Scene Change Detection

Scene change detection (SCD) refers to the task of localizing changes and identifying change-categories given two scenes. A scene can be either an RGB (+D) image or a 3D reconstruction (point cloud). If the scene is an image, SCD is a form of pixel-level prediction because each pixel in the image is classified according to a category. On the other hand, if the scene is point cloud, SCD is a form of point-level prediction because each point in the cloud is classified according to a category.

Some example benchmarks for this task are VL-CMU-CD, PCD, and CD2014. Recently, more complicated benchmarks such as ChangeSim, HDMap, and Mallscape are released.

Models are usually evaluated with the Mean Intersection-Over-Union (Mean IoU), Pixel Accuracy, or F1 metrics.

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 1–25 of 25 papers

TitleStatusHype
Towards Generalizable Scene Change DetectionCode2
Zero-Shot Scene Change DetectionCode2
Robust Scene Change Detection Using Visual Foundation Models and Cross-Attention MechanismsCode1
Unsupervised Change Detection for Space Habitats Using 3D Point CloudsCode1
SARAS-Net: Scale and Relation Aware Siamese Network for Change DetectionCode1
Differencing based Self-supervised pretraining for Scene Change DetectionCode1
How to Reduce Change Detection to Semantic SegmentationCode1
ChangeSim: Towards End-to-End Online Scene Change Detection in Industrial Indoor EnvironmentsCode1
DR-TANet: Dynamic Receptive Temporal Attention Network for Street Scene Change DetectionCode1
Multi-Temporal Scene Classification and Scene Change Detection with Correlation based FusionCode1
EMPLACE: Self-Supervised Urban Scene Change DetectionCode0
Towards Generalizable Scene Change Detection—0
ZeroSCD: Zero-Shot Street Scene Change Detection—0
A Category Agnostic Model for Visual Rearrangment—0
SeaDSC: A video-based unsupervised method for dynamic scene change detection in unmanned surface vehicles—0
Industrial Scene Change Detection using Deep Convolutional Neural Networks—0
Scene Change Detection Using Multiscale Cascade Residual Convolutional Neural Networks—0
Crowd Source Scene Change Detection and Local Map Update—0
Shot boundary detection method based on a new extensive dataset and mixed features—0
City-scale Scene Change Detection using Point Clouds—0
Hierarchical Paired Channel Fusion Network for Street Scene Change Detection—0
Epipolar-Guided Deep Object Matching for Scene Change Detection—0
Weakly Supervised Silhouette-based Semantic Scene Change DetectionCode0
Learning to Measure Change: Fully Convolutional Siamese Metric Networks for Scene Change DetectionCode0
Topological map construction and scene recognition for vehicle localization—0
Show:102550
All datasetsChangeSimPCDUnaligned-VL-CMU-CD (neighbor distance 2)VL-CMU-CDChangeVPRSemantic Scene Understanding Challenge (passive actuation & ground-truth localisation)

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1C-3POCategory mIoU27.8—Unverified
2RTABMAP+CSCDNetCategory mIoU26.1—Unverified
3RTABMAP+ChangeNetCategory mIoU23—Unverified
#ModelMetricClaimedVerifiedStatus
1C-3PO (VGG-16)F1-score0.83—Unverified
2C-3PO (ResNet-18)F1-score0.82—Unverified
#ModelMetricClaimedVerifiedStatus
1Robust-Scene-Change-Detection (Diff-View Augmentation)F1-score0.78—Unverified
2Robust-Scene-Change-DetectionF1-score0.74—Unverified
#ModelMetricClaimedVerifiedStatus
1C-3PO (VGG-16)F1-score0.8—Unverified
2C-3PO (ResNet-18)F1-score0.79—Unverified
#ModelMetricClaimedVerifiedStatus
1GeSCF (zero-shot)F1 score58.2—Unverified
#ModelMetricClaimedVerifiedStatus
1Demo_SCDOMQ0.02—Unverified