3D Instance Segmentation

Description from the archive archive 2025-07-28.

Benchmarks archive 2025-07-28

9 leaderboard tables shown for this task, 9 with rows (a “benchmark” on this site is a table with at least one row, as on /sota), ordered by row count. “Best model” is the first row in the archive's own order at snapshot; nothing is re-ranked here and metric direction is not recorded in the archive. PwC's Trend sparklines are not in the archive, so that column is omitted.

Syntology column: samples harvested from the paper's repositories and executed on synthesized fixtures; “ran” is not a correctness claim and does not order the table. A dash means no Syntology record for that paper, not a recorded non-run. Read from the graph 2026-09-24.

Libraries

Not in the archive: the export carries no per-task library table, so there is nothing to show at snapshot 2025-07-28.

Datasets archive 2025-07-28

18 datasets whose archive record lists this task, ordered by the archive's paper count.

Subtasks archive 2025-07-28

1 subtask in the archive's task tree.

Parent tasks archive 2025-07-28

Most implemented papers archive 2025-07-28

30 shown of 73 papers with code (153 tagged with this task in all), ordered by repositories listed in the archive, not by stars (the archive holds no stars, so PwC's “Social” and “Latest” sorts cannot be reproduced). Papers without a page here are shown as plain text.

• Mask R-CNN
  20 Mar 2017 179 repositories listed Syntology ran 42 of 140 samples · 98 unverified · 23 pointer-only (licence)
  Our approach efficiently detects objects in an image while simultaneously generating a high-quality segmentation mask for each instance.
• 3D U-Net: Learning Dense Volumetric Segmentation from Sparse Annotation
  21 Jun 2016 27 repositories listed Syntology ran 53 of 76 samples · 23 unverified · 20 pointer-only (licence)
  This paper introduces a network for volumetric segmentation that learns from sparsely annotated volumetric images.
• PointCNN: Convolution On 𝒳-Transformed Points
  23 Jan 2018 16 repositories listed
  The proposed method is a generalization of typical CNNs to feature learning from point clouds, thus we call it PointCNN.
• PartNet: A Large-scale Benchmark for Fine-grained and Hierarchical Part-level 3D Object Understanding
  6 Dec 2018 5 repositories listed
  We present PartNet: a consistent, large-scale dataset of 3D objects annotated with fine-grained, instance-level, and hierarchical 3D part information.
• STPLS3D: A Large-Scale Synthetic and Real Aerial Photogrammetry 3D Point Cloud Dataset
  17 Mar 2022 4 repositories listed Syntology ran 4 of 23 samples · 19 unverified · 3 pointer-only (licence)
  Specifically, we introduce a synthetic aerial photogrammetry point clouds generation pipeline that takes full advantage of open geospatial data sources and off-the-shelf commercial packages.
• PointGroup: Dual-Set Point Grouping for 3D Instance Segmentation
  3 Apr 2020 4 repositories listed Syntology ran 0 of 5 samples · 5 unverified
  Instance segmentation is an important task for scene understanding.
• Spherical Kernel for Efficient Graph Convolution on 3D Point Clouds
  20 Sep 2019 3 repositories listed Syntology ran 1 of 11 samples · 10 unverified
  We propose a spherical kernel for efficient graph convolution of 3D point clouds.
• Associatively Segmenting Instances and Semantics in Point Clouds
  26 Feb 2019 3 repositories listed
  A 3D point cloud describes the real scene precisely and intuitively.
• ISBNet: a 3D Point Cloud Instance Segmentation Network with Instance-aware Sampling and Box-aware Dynamic Convolution
  1 Mar 2023 2 repositories listed Syntology ran 2 of 19 samples · 17 unverified
  Existing 3D instance segmentation methods are predominated by the bottom-up design -- manually fine-tuned algorithm to group points into clusters followed by a refinement network.
• JSNet: Joint Instance and Semantic Segmentation of 3D Point Clouds
  20 Dec 2019 2 repositories listed
  In this paper, we propose a novel joint instance and semantic segmentation approach, which is called JSNet, in order to address the instance and semantic segmentation of 3D point clouds simultaneously.
• Sketchy Bounding-box Supervision for 3D Instance Segmentation
  22 May 2025 1 repository listed
  Bounding box supervision has gained considerable attention in weakly supervised 3D instance segmentation.
• Wheat3DGS: In-field 3D Reconstruction, Instance Segmentation and Phenotyping of Wheat Heads with Gaussian Splatting
  9 Apr 2025 1 repository listed
  Automated extraction of plant morphological traits is crucial for supporting crop breeding and agricultural management through high-throughput field phenotyping (HTFP).
• CLIMB-3D: Continual Learning for Imbalanced 3D Instance Segmentation
  24 Feb 2025 1 repository listed
  While 3D instance segmentation (3DIS) has advanced significantly, existing methods typically assume that all object classes are known in advance and are uniformly distributed.
• Relation3D : Enhancing Relation Modeling for Point Cloud Instance Segmentation
  1 Jan 2025 1 repository listed
  3D instance segmentation aims to predict a set of object instances in a scene, representing them as binary foreground masks with corresponding semantic labels.
• Horticultural Temporal Fruit Monitoring via 3D Instance Segmentation and Re-Identification using Point Clouds
  12 Nov 2024 1 repository listed
  Experimental results on a real dataset of strawberries demonstrate that our approach outperforms other methods for fruits re-identification over time, allowing for precise temporal fruit monitoring in real and complex…
• SA3DIP: Segment Any 3D Instance with Potential 3D Priors
  6 Nov 2024 1 repository listed
  Thus, we present ScanNetV2-INS with complete ground truth labels and supplement additional instances for 3D class-agnostic instance segmentation.
• EmbodiedSAM: Online Segment Any 3D Thing in Real Time
  21 Aug 2024 1 repository listed
  In this paper, we aim to leverage Segment Anything Model (SAM) for real-time 3D instance segmentation in an online setting.
• SGIFormer: Semantic-guided and Geometric-enhanced Interleaving Transformer for 3D Instance Segmentation
  16 Jul 2024 1 repository listed
  Specifically, the principle of our SMQ initialization scheme is to leverage the predicted voxel-wise semantic information to implicitly generate the scene-aware query, yielding adequate scene prior and compensating for…
• Part2Object: Hierarchical Unsupervised 3D Instance Segmentation
  14 Jul 2024 1 repository listed Syntology ran 5 of 10 samples · 5 unverified
  By training Hi-Mask3D on the objects and object parts extracted from Part2Object, we achieve consistent and superior performance compared to state-of-the-art models in various settings, including unsupervised instance…
• Instance Consistency Regularization for Semi-Supervised 3D Instance Segmentation
  24 Jun 2024 1 repository listed
  To leverage unlabeled data, previous semi-supervised 3D instance segmentation approaches have explored self-training frameworks, which rely on high-quality pseudo labels for consistency regularization.
• Open-YOLO 3D: Towards Fast and Accurate Open-Vocabulary 3D Instance Segmentation
  4 Jun 2024 1 repository listed Syntology ran 4 of 11 samples · 7 unverified · 11 pointer-only (licence)
  To this end, we propose a fast yet accurate open-vocabulary 3D instance segmentation approach, named Open-YOLO 3D, that effectively leverages only 2D object detection from multi-view RGB images for open-vocabulary 3D…
• AutoInst: Automatic Instance-Based Segmentation of LiDAR 3D Scans
  24 Mar 2024 1 repository listed
  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…
• BSNet: Box-Supervised Simulation-assisted Mean Teacher for 3D Instance Segmentation
  22 Mar 2024 1 repository listed Syntology ran 3 of 6 samples · 3 unverified · 6 pointer-only (licence)
  To generate higher quality pseudo-labels and achieve more precise weakly supervised 3DIS results, we propose the Box-Supervised Simulation-assisted Mean Teacher for 3D Instance Segmentation (BSNet), which devises a…
• ENSTRECT: A Stage-based Approach to 2.5D Structural Damage Detection
  6 Jan 2024 1 repository listed
  Using these inputs, surface damages are segmented at the image level and then mapped into the point cloud space, resulting in a segmented point cloud.
• ODIN: A Single Model for 2D and 3D Segmentation
  4 Jan 2024 1 repository listed Syntology ran 3 of 8 samples · 5 unverified
  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
  18 Dec 2023 1 repository listed Syntology ran 1 of 4 samples · 3 unverified
  We also introduce two margin-based losses for the point migration to enforce corrections for the false positives/negatives and cohesion of foreground points, significantly improving the performance.
• Open3DIS: Open-Vocabulary 3D Instance Segmentation with 2D Mask Guidance
  17 Dec 2023 1 repository listed Syntology ran 8 of 8 samples · 0 unverified
  We introduce Open3DIS, a novel solution designed to tackle the problem of Open-Vocabulary Instance Segmentation within 3D scenes.
• MWSIS: Multimodal Weakly Supervised Instance Segmentation with 2D Box Annotations for Autonomous Driving
  12 Dec 2023 1 repository listed
  Instance segmentation is a fundamental research in computer vision, especially in autonomous driving.
• PartSLIP++: Enhancing Low-Shot 3D Part Segmentation via Multi-View Instance Segmentation and Maximum Likelihood Estimation
  5 Dec 2023 1 repository listed Syntology ran 17 of 17 samples · 0 unverified
  Open-world 3D part segmentation is pivotal in diverse applications such as robotics and AR/VR.
• OneFormer3D: One Transformer for Unified Point Cloud Segmentation
  24 Nov 2023 1 repository listed
  Semantic, instance, and panoptic segmentation of 3D point clouds have been addressed using task-specific models of distinct design.

Syntology lines on 13 of the papers shown; no Syntology record for the others (a paper without an arXiv id cannot be joined to the graph, and absence from the graph layer is not a recorded non-run). “Ran” means the sample executed on a synthesized fixture, not that the paper's result was reproduced. Read from the graph 2026-09-24.