# DyCo3D: Robust Instance Segmentation of 3D Point Clouds through Dynamic Convolution

arXiv: https://arxiv.org/abs/2011.13328 · HTML: https://mlsanity.com/paper/2011.13328/

## Key facts

- Cited by 75 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 26 Nov 2020.

## Built on by (most cited first, 30 of 75)

- [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)
- [Open3DIS: Open-Vocabulary 3D Instance Segmentation with 2D Mask Guidance](https://mlsanity.com/paper/2312.10671/) (2023)
- [Superpoint Transformer for 3D Scene Instance Segmentation](https://mlsanity.com/paper/2211.15766/) (2022)
- [OneFormer3D: One Transformer for Unified Point Cloud Segmentation](https://mlsanity.com/paper/2311.14405/) (2023)
- [ISBNet: a 3D Point Cloud Instance Segmentation Network with Instance-aware Sampling and Box-aware Dynamic Convolution](https://mlsanity.com/paper/2303.00246/) (2023)
- [Mask-Attention-Free Transformer for 3D Instance Segmentation](https://mlsanity.com/paper/2309.01692/) (2023)
- [3D Instances as 1D Kernels](https://mlsanity.com/paper/2207.07372/) (2022)
- [AGILE3D: Attention Guided Interactive Multi-object 3D Segmentation](https://mlsanity.com/paper/2306.00977/) (2023)
- [Four Ways to Improve Verbo-visual Fusion for Dense 3D Visual Grounding](https://mlsanity.com/paper/2309.04561/) (2023)
- [Top-Down Beats Bottom-Up in 3D Instance Segmentation](https://mlsanity.com/paper/2302.02871/) (2023)
- [Deep Learning Based 3D Segmentation: A Survey](https://mlsanity.com/paper/2103.05423/) (2021)
- [MaskGroup: Hierarchical Point Grouping and Masking for 3D Instance Segmentation](https://mlsanity.com/paper/2203.14662/) (2022)
- [Open-YOLO 3D: Towards Fast and Accurate Open-Vocabulary 3D Instance Segmentation](https://mlsanity.com/paper/2406.02548/) (2024)
- [PO3AD: Predicting Point Offsets toward Better 3D Point Cloud Anomaly Detection](https://mlsanity.com/paper/2412.12617/) (2024)
- [Divide and Conquer: 3D Point Cloud Instance Segmentation With Point-Wise Binarization](https://mlsanity.com/paper/2207.11209/) (2022)
- [UrbanBIS: a Large-scale Benchmark for Fine-grained Urban Building Instance Segmentation](https://mlsanity.com/paper/2305.02627/) (2023)
- [Spherical Mask: Coarse-to-Fine 3D Point Cloud Instance Segmentation with Spherical Representation](https://mlsanity.com/paper/2312.11269/) (2023)
- [ODAM: Object Detection, Association, and Mapping using Posed RGB Video](https://mlsanity.com/paper/2108.10165/) (2021)
- [Point Scene Understanding via Disentangled Instance Mesh Reconstruction](https://mlsanity.com/paper/2203.16832/) (2022)
- [UniDet3D: Multi-dataset Indoor 3D Object Detection](https://mlsanity.com/paper/2409.04234/) (2024)
- [Human-centric Scene Understanding for 3D Large-scale Scenarios](https://mlsanity.com/paper/2307.14392/) (2023)
- [LitePT: Lighter Yet Stronger Point Transformer](https://mlsanity.com/paper/2512.13689/) (2025)
- [PointInst3D: Segmenting 3D Instances by Points](https://mlsanity.com/paper/2204.11402/) (2022)
- [Scalable SoftGroup for 3D Instance Segmentation on Point Clouds](https://mlsanity.com/paper/2209.08263/) (2022)
- [A Unified Framework for 3D Scene Understanding](https://mlsanity.com/paper/2407.03263/) (2024)
- [Any3DIS: Class-Agnostic 3D Instance Segmentation by 2D Mask Tracking](https://mlsanity.com/paper/2411.16183/) (2024)
- [3D-QueryIS: A Query-based Framework for 3D Instance Segmentation](https://mlsanity.com/paper/2211.09375/) (2022)
- [Scalable 3D Panoptic Segmentation As Superpoint Graph Clustering](https://mlsanity.com/paper/2401.06704/) (2024)
- [Segment Any 3D Object with Language](https://mlsanity.com/paper/2404.02157/) (2024)

## Abstract (arXiv)

Previous top-performing approaches for point cloud instance segmentation involve a bottom-up strategy, which often includes inefficient operations or complex pipelines, such as grouping over-segmented components, introducing additional steps for refining, or designing complicated loss functions. The inevitable variation in the instance scales can lead bottom-up methods to become particularly sensitive to hyper-parameter values. To this end, we propose instead a dynamic, proposal-free, data-driven approach that generates the appropriate convolution kernels to apply in response to the nature of the instances. To make the kernels discriminative, we explore a large context by gathering homogeneous points that share identical semantic categories and have close votes for the geometric centroids. Instances are then decoded by several simple convolutional layers. Due to the limited receptive field introduced by the sparse convolution, a small light-weight transformer is also devised to capture the long-range dependencies and high-level interactions among point samples. The proposed method achieves promising results on both ScanetNetV2 and S3DIS, and this performance is robust to the particular hyper-parameter values chosen. It also improves inference speed by more than 25% over the current state-of-the-art. Code is available at: https://git.io/DyCo3D