3D Instance Segmentation
55 papers with code • 8 benchmarks • 13 datasets
Image: OccuSeg
Libraries
Use these libraries to find 3D Instance Segmentation models and implementationsLatest papers with no code
AutoInst: Automatic Instance-Based Segmentation of LiDAR 3D Scans
To this end, we construct a learning framework consisting of two components: (1) a pseudo-annotation scheme for generating initial unsupervised pseudo-labels; and (2) a self-training algorithm for instance segmentation to fit robust, accurate instances from initial noisy proposals.
MaskClustering: View Consensus based Mask Graph Clustering for Open-Vocabulary 3D Instance Segmentation
The corresponding 3D points cluster of these 2D mask clusters can be regarded as 3D instances, along with the fused open-vocabulary features from clustered 2D masks.
Multi-View 3D Instance Segmentation of Structural Anomalies for Enhanced Structural Inspection of Concrete Bridges
Granted a localization tolerance of 4cm, IoUs of over 90% can be achieved for crack and corrosion and 41% for spalling, which appears to be a specifically challenging class.
ODIN: A Single Model for 2D and 3D Perception
The gap in performance between methods that consume posed images versus post-processed 3D point clouds has fueled the belief that 2D and 3D perception require distinct model architectures.
Spherical Mask: Coarse-to-Fine 3D Point Cloud Instance Segmentation with Spherical Representation
Coarse-to-fine 3D instance segmentation methods show weak performances compared to recent Grouping-based, Kernel-based and Transformer-based methods.
Open3DIS: Open-vocabulary 3D Instance Segmentation with 2D Mask Guidance
We introduce Open3DIS, a novel solution designed to tackle the problem of Open-Vocabulary Instance Segmentation within 3D scenes.
SAI3D: Segment Any Instance in 3D Scenes
Advancements in 3D instance segmentation have traditionally been tethered to the availability of annotated datasets, limiting their application to a narrow spectrum of object categories.
SAM-guided Graph Cut for 3D Instance Segmentation
Experimental results on the ScanNet, ScanNet++ and KITTI-360 datasets demonstrate that our method achieves robust segmentation performance and can generalize across different types of scenes.
EipFormer: Emphasizing Instance Positions in 3D Instance Segmentation
It enhances the initial instance positions through weighted farthest point sampling and further refines the instance positions and proposals using aggregation averaging and center matching.
Three Ways to Improve Verbo-visual Fusion for Dense 3D Visual Grounding
A common formulation to tackle 3D visual grounding is grounding-by-detection, where localization is done via bounding boxes.