3D Instance Segmentation
9개 벤치마크 · 논문 187편 · 이 태스크의 논문 보기 →
Benchmarks
ScanNet(v2)
S3DIS
STPLS3D
ScanNet200
PartNet
ScanNet++
SceneNN
MitoEM
ScanNet
Most implemented
Mask R-CNN
3D U-Net: Learning Dense Volumetric Segmentation from Sparse Annotation
PointCNN: Convolution On $\mathcal{X}$-Transformed Points
PartNet: A Large-scale Benchmark for Fine-grained and Hierarchical Part-level 3D Object Understanding
STPLS3D: A Large-Scale Synthetic and Real Aerial Photogrammetry 3D Point Cloud Dataset
PointGroup: Dual-Set Point Grouping for 3D Instance Segmentation
Papers
AQ3D: Adaptive Query Transformer for 3D Instance Segmentation
Transformer-based decoders for 3D instance segmentation typically commit to a fixed number of queries and positional modeling calibrated on the training distribution rather than on the scene at hand. Indoor scans vary wi…
3D Instance SegmentationData AugmentationConsistent Scene Understanding in 3D Gaussian Splatting via Multi-Cue Mask Refinement
Reliable instance-level scene understanding is a fundamental prerequisite for object-level interactions and high-fidelity 3D representations. While current methods often leverage 2D foundation segmentation models to obta…
3D Instance SegmentationScene UnderstandingGVC-Seg: Training-Free 3D Instance Segmentation via Geometric Visual Correspondence
Accurate 3D instance segmentation in point cloud data is critical for machine vision applications. Recent advancements leverage multiple pre-trained foundation models to generate 3D proposals, followed by the application…
3D Instance SegmentationSemantic SegmentationEnsemble LearningESAM++: Efficient Online 3D Perception on the Edge
Online 3D scene perception in real time is essential for robotics, AR/VR, and autonomous systems, particularly in edge computing scenarios where computational resources are limited and privacy is crucial. Recent state-of…
3D Instance SegmentationPoint CloudsEvObj: Learning Evolving Object-centric Representations for 3D Instance Segmentation without Scene Supervision
We introduce EvObj for unsupervised 3D instance segmentation that bridges the geometric domain gap between synthetic pretraining data and real-world point clouds. Current methods suffer from structural discrepancies when…
3D Instance SegmentationObject SegmentationPoint CloudsSpaCeFormer: Fast Proposal-Free Open-Vocabulary 3D Instance Segmentation
Open-vocabulary 3D instance segmentation is a core capability for robotics and AR/VR, but prior methods trade one bottleneck for another: multi-stage 2D+3D pipelines aggregate foundation-model outputs at hundreds of seco…
3D Instance Segmentation