PointHR: Exploring High-Resolution Architectures for 3D Point Cloud
Segmentation
- URL: http://arxiv.org/abs/2310.07743v1
- Date: Wed, 11 Oct 2023 09:29:17 GMT
- Title: PointHR: Exploring High-Resolution Architectures for 3D Point Cloud
Segmentation
- Authors: Haibo Qiu, Baosheng Yu, Yixin Chen, Dacheng Tao
- Abstract summary: We explore high-resolution architectures for 3D point cloud segmentation.
We propose a unified pipeline named PointHR, which includes a knn-based sequence operator for feature extraction and a differential resampling operator.
To evaluate these architectures for dense point cloud analysis, we conduct thorough experiments using S3DIS and ScanNetV2 datasets.
- Score: 77.44144260601182
- License: http://creativecommons.org/licenses/by-nc-sa/4.0/
- Abstract: Significant progress has been made recently in point cloud segmentation
utilizing an encoder-decoder framework, which initially encodes point clouds
into low-resolution representations and subsequently decodes high-resolution
predictions. Inspired by the success of high-resolution architectures in image
dense prediction, which always maintains a high-resolution representation
throughout the entire learning process, we consider it also highly important
for 3D dense point cloud analysis. Therefore, in this paper, we explore
high-resolution architectures for 3D point cloud segmentation. Specifically, we
generalize high-resolution architectures using a unified pipeline named
PointHR, which includes a knn-based sequence operator for feature extraction
and a differential resampling operator to efficiently communicate different
resolutions. Additionally, we propose to avoid numerous on-the-fly computations
of high-resolution architectures by pre-computing the indices for both sequence
and resampling operators. By doing so, we deliver highly competitive
high-resolution architectures while capitalizing on the benefits of
well-designed point cloud blocks without additional effort. To evaluate these
architectures for dense point cloud analysis, we conduct thorough experiments
using S3DIS and ScanNetV2 datasets, where the proposed PointHR outperforms
recent state-of-the-art methods without any bells and whistles. The source code
is available at \url{https://github.com/haibo-qiu/PointHR}.
Related papers
- V-DETR: DETR with Vertex Relative Position Encoding for 3D Object
Detection [73.37781484123536]
We introduce a highly performant 3D object detector for point clouds using the DETR framework.
To address the limitation, we introduce a novel 3D Relative Position (3DV-RPE) method.
We show exceptional results on the challenging ScanNetV2 benchmark.
arXiv Detail & Related papers (2023-08-08T17:14:14Z) - 3D Cascade RCNN: High Quality Object Detection in Point Clouds [122.42455210196262]
We present 3D Cascade RCNN, which allocates multiple detectors based on the voxelized point clouds in a cascade paradigm.
We validate the superiority of our proposed 3D Cascade RCNN, when comparing to state-of-the-art 3D object detection techniques.
arXiv Detail & Related papers (2022-11-15T15:58:36Z) - Learning Local Displacements for Point Cloud Completion [93.54286830844134]
We propose a novel approach aimed at object and semantic scene completion from a partial scan represented as a 3D point cloud.
Our architecture relies on three novel layers that are used successively within an encoder-decoder structure.
We evaluate both architectures on object and indoor scene completion tasks, achieving state-of-the-art performance.
arXiv Detail & Related papers (2022-03-30T18:31:37Z) - PointAttN: You Only Need Attention for Point Cloud Completion [89.88766317412052]
Point cloud completion refers to completing 3D shapes from partial 3D point clouds.
We propose a novel neural network for processing point cloud in a per-point manner to eliminate kNNs.
The proposed framework, namely PointAttN, is simple, neat and effective, which can precisely capture the structural information of 3D shapes.
arXiv Detail & Related papers (2022-03-16T09:20:01Z) - A Holistically-Guided Decoder for Deep Representation Learning with
Applications to Semantic Segmentation and Object Detection [74.88284082187462]
One common strategy is to adopt dilated convolutions in the backbone networks to extract high-resolution feature maps.
We propose one novel holistically-guided decoder which is introduced to obtain the high-resolution semantic-rich feature maps.
arXiv Detail & Related papers (2020-12-18T10:51:49Z) - Exploring Deep 3D Spatial Encodings for Large-Scale 3D Scene
Understanding [19.134536179555102]
We propose an alternative approach to overcome the limitations of CNN based approaches by encoding the spatial features of raw 3D point clouds into undirected graph models.
The proposed method achieves on par state-of-the-art accuracy with improved training time and model stability thus indicating strong potential for further research.
arXiv Detail & Related papers (2020-11-29T12:56:19Z)
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.