# MASC: Multi-scale Affinity with Sparse Convolution for 3D Instance Segmentation

arXiv: https://arxiv.org/abs/1902.04478 · HTML: https://mlsanity.com/paper/1902.04478/

## Key facts

- Cited by 25 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 12 Feb 2019.

## Built on by (most cited first, 25 of 25)

- [Mask3D: Mask Transformer for 3D Semantic Instance Segmentation](https://mlsanity.com/paper/2210.03105/) (2022)
- [SoftGroup for 3D Instance Segmentation on Point Clouds](https://mlsanity.com/paper/2203.01509/) (2022)
- [Hierarchical Aggregation for 3D Instance Segmentation](https://mlsanity.com/paper/2108.02350/) (2021)
- [AGILE3D: Attention Guided Interactive Multi-object 3D Segmentation](https://mlsanity.com/paper/2306.00977/) (2023)
- [Deep Learning Based 3D Segmentation: A Survey](https://mlsanity.com/paper/2103.05423/) (2021)
- [3D Segmentation of Humans in Point Clouds with Synthetic Data](https://mlsanity.com/paper/2212.00786/) (2022)
- [PointInst3D: Segmenting 3D Instances by Points](https://mlsanity.com/paper/2204.11402/) (2022)
- [Point Cloud Instance Segmentation with Semi-supervised Bounding-Box Mining](https://mlsanity.com/paper/2111.15210/) (2021)
- [Scalable SoftGroup for 3D Instance Segmentation on Point Clouds](https://mlsanity.com/paper/2209.08263/) (2022)
- [3D-QueryIS: A Query-based Framework for 3D Instance Segmentation](https://mlsanity.com/paper/2211.09375/) (2022)
- [ForestFormer3D: A Unified Framework for End-to-End Segmentation of Forest LiDAR 3D Point Clouds](https://mlsanity.com/paper/2506.16991/) (2025)
- [3D Instance Segmentation of MVS Buildings](https://mlsanity.com/paper/2112.09902/) (2021)
- [HIDA: Towards Holistic Indoor Understanding for the Visually Impaired via Semantic Instance Segmentation with a Wearable Solid-State LiDAR Sensor](https://mlsanity.com/paper/2107.03180/) (2021)
- [When 3D Bounding-Box Meets SAM: Point Cloud Instance Segmentation with Weak-and-Noisy Supervision](https://mlsanity.com/paper/2309.00828/) (2023)
- [A Review of Panoptic Segmentation for Mobile Mapping Point Clouds](https://mlsanity.com/paper/2304.13980/) (2023)
- [ClickSeg: 3D Instance Segmentation with Click-Level Weak Annotations](https://mlsanity.com/paper/2307.09732/) (2023)
- [Collaborative Propagation on Multiple Instance Graphs for 3D Instance Segmentation with Single-point Supervision](https://mlsanity.com/paper/2208.05110/) (2022)
- [Dynamic Convolution for 3D Point Cloud Instance Segmentation](https://mlsanity.com/paper/2107.08392/) (2021)
- [Scan2Part: Fine-grained and Hierarchical Part-level Understanding of Real-World 3D Scans](https://mlsanity.com/paper/2206.02366/) (2022)
- [Weakly Supervised 3D Instance Segmentation without Instance-level Annotations](https://mlsanity.com/paper/2308.01721/) (2023)
- [Advancements in Point Cloud-Based 3D Defect Detection and Classification for Industrial Systems: A Comprehensive Survey](https://mlsanity.com/paper/2402.12923/) (2024)
- [SegmentAnyTreeV2: Scaling Transformer-Based Tree Instance Segmentation Across Sensors, Platforms, and Forests](https://mlsanity.com/paper/2606.08206/) (2026)
- [Semantic Segmentation-Assisted Instance Feature Fusion for Multi-Level 3D Part Instance Segmentation](https://mlsanity.com/paper/2208.04766/) (2022)
- [BEEP3D: Box-Supervised End-to-End Pseudo-Mask Generation for 3D Instance Segmentation](https://mlsanity.com/paper/2510.12182/) (2025)
- [PSGformer: Enhancing 3D Point Cloud Instance Segmentation via Precise Semantic Guidance](https://mlsanity.com/paper/2307.07708/) (2023)

## Abstract (arXiv)

We propose a new approach for 3D instance segmentation based on sparse convolution and point affinity prediction, which indicates the likelihood of two points belonging to the same instance. The proposed network, built upon submanifold sparse convolution [3], processes a voxelized point cloud and predicts semantic scores for each occupied voxel as well as the affinity between neighboring voxels at different scales. A simple yet effective clustering algorithm segments points into instances based on the predicted affinity and the mesh topology. The semantic for each instance is determined by the semantic prediction. Experiments show that our method outperforms the state-of-the-art instance segmentation methods by a large margin on the widely used ScanNet benchmark [2]. We share our code publicly at https://github.com/art-programmer/MASC.