Learning Gaussian Instance Segmentation in Point Clouds
- URL: http://arxiv.org/abs/2007.09860v1
- Date: Mon, 20 Jul 2020 03:11:32 GMT
- Title: Learning Gaussian Instance Segmentation in Point Clouds
- Authors: Shih-Hung Liu, Shang-Yi Yu, Shao-Chi Wu, Hwann-Tzong Chen, Tyng-Luh
Liu
- Abstract summary: This paper presents a novel method for instance segmentation of 3D point clouds.
The proposed method is called Gaussian Instance Center Network (GICN), which can approximate the distributions of instance centers scattered in the whole scene as Gaussian center heatmaps.
Our method achieves state-of-the-art performance in the task of 3D instance segmentation on ScanNet and S3DIS datasets.
- Score: 26.711177503253946
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: This paper presents a novel method for instance segmentation of 3D point
clouds. The proposed method is called Gaussian Instance Center Network (GICN),
which can approximate the distributions of instance centers scattered in the
whole scene as Gaussian center heatmaps. Based on the predicted heatmaps, a
small number of center candidates can be easily selected for the subsequent
predictions with efficiency, including i) predicting the instance size of each
center to decide a range for extracting features, ii) generating bounding boxes
for centers, and iii) producing the final instance masks. GICN is a
single-stage, anchor-free, and end-to-end architecture that is easy to train
and efficient to perform inference. Benefited from the center-dictated
mechanism with adaptive instance size selection, our method achieves
state-of-the-art performance in the task of 3D instance segmentation on ScanNet
and S3DIS datasets.
Related papers
- Bayesian Self-Training for Semi-Supervised 3D Segmentation [59.544558398992386]
3D segmentation is a core problem in computer vision.
densely labeling 3D point clouds to employ fully-supervised training remains too labor intensive and expensive.
Semi-supervised training provides a more practical alternative, where only a small set of labeled data is given, accompanied by a larger unlabeled set.
arXiv Detail & Related papers (2024-09-12T14:54:31Z) - ShapeSplat: A Large-scale Dataset of Gaussian Splats and Their Self-Supervised Pretraining [104.34751911174196]
We build a large-scale dataset of 3DGS using ShapeNet and ModelNet datasets.
Our dataset ShapeSplat consists of 65K objects from 87 unique categories.
We introduce textbftextitGaussian-MAE, which highlights the unique benefits of representation learning from Gaussian parameters.
arXiv Detail & Related papers (2024-08-20T14:49:14Z) - AutoInst: Automatic Instance-Based Segmentation of LiDAR 3D Scans [41.17467024268349]
Making sense of 3D environments requires fine-grained scene understanding.
We propose to predict instance segmentations for 3D scenes in an unsupervised way.
Our approach attains 13.3% higher Average Precision and 9.1% higher F1 score compared to the best-performing baseline.
arXiv Detail & Related papers (2024-03-24T22:53:16Z) - Semantic Segmentation-Assisted Instance Feature Fusion for Multi-Level
3D Part Instance Segmentation [17.929866369256555]
We present a new method for 3D part instance segmentation.
Our method exploits semantic segmentation to fuse nonlocal instance features, such as center prediction.
Our method outperforms existing methods with a large-margin improvement in the PartNet benchmark.
arXiv Detail & Related papers (2022-08-09T13:22:55Z) - PointInst3D: Segmenting 3D Instances by Points [136.7261709896713]
We propose a fully-convolutional 3D point cloud instance segmentation method that works in a per-point prediction fashion.
We find the key to its success is assigning a suitable target to each sampled point.
Our approach achieves promising results on both ScanNet and S3DIS benchmarks.
arXiv Detail & Related papers (2022-04-25T02:41:46Z) - SE(3)-Equivariant Attention Networks for Shape Reconstruction in
Function Space [50.14426188851305]
We propose the first SE(3)-equivariant coordinate-based network for learning occupancy fields from point clouds.
In contrast to previous shape reconstruction methods that align the input to a regular grid, we operate directly on the irregular, unoriented point cloud.
We show that our method outperforms previous SO(3)-equivariant methods, as well as non-equivariant methods trained on SO(3)-augmented datasets.
arXiv Detail & Related papers (2022-04-05T17:59:15Z) - MaskGroup: Hierarchical Point Grouping and Masking for 3D Instance
Segmentation [36.28586460186891]
This paper studies the 3D instance segmentation problem, which has a variety of real-world applications such as robotics and augmented reality.
We propose a novel framework to group and refine the 3D instances.
Our approach achieves a 66.4% mAP with the 0.5 IoU threshold on the ScanNetV2 test set, which is 1.9% higher than the state-of-the-art method.
arXiv Detail & Related papers (2022-03-28T11:22:58Z) - Learning Semantic Segmentation of Large-Scale Point Clouds with Random
Sampling [52.464516118826765]
We introduce RandLA-Net, an efficient and lightweight neural architecture to infer per-point semantics for large-scale point clouds.
The key to our approach is to use random point sampling instead of more complex point selection approaches.
Our RandLA-Net can process 1 million points in a single pass up to 200x faster than existing approaches.
arXiv Detail & Related papers (2021-07-06T05:08:34Z) - DyCo3D: Robust Instance Segmentation of 3D Point Clouds through Dynamic
Convolution [136.7261709896713]
We propose a data-driven approach that generates the appropriate convolution kernels to apply in response to the nature of the instances.
The proposed method achieves promising results on both ScanetNetV2 and S3DIS.
It also improves inference speed by more than 25% over the current state-of-the-art.
arXiv Detail & Related papers (2020-11-26T14:56:57Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.