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

11/26/2020
by   Tong He, et al.
0

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 state-of-the-art. Code is available at: https://git.io/DyCo3D

READ FULL TEXT

page 3

page 7

page 9

research
07/18/2021

Dynamic Convolution for 3D Point Cloud Instance Segmentation

We propose an approach to instance segmentation from 3D point clouds bas...
research
02/12/2019

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

We propose a new approach for 3D instance segmentation based on sparse c...
research
07/15/2022

3D Instances as 1D Kernels

We introduce a 3D instance representation, termed instance kernels, wher...
research
10/06/2022

Mask3D for 3D Semantic Instance Segmentation

Modern 3D semantic instance segmentation approaches predominantly rely o...
research
04/25/2022

PointInst3D: Segmenting 3D Instances by Points

The current state-of-the-art methods in 3D instance segmentation typical...
research
11/17/2022

3D-QueryIS: A Query-based Framework for 3D Instance Segmentation

Previous top-performing methods for 3D instance segmentation often maint...
research
07/22/2022

Divide and Conquer: 3D Point Cloud Instance Segmentation With Point-Wise Binarization

Instance segmentation on point clouds is crucially important for 3D scen...

Please sign up or login with your details

Forgot password? Click here to reset