Point Transformer
Self-attention networks have revolutionized natural language processing and are making impressive strides in image analysis tasks such as image classification and object detection. Inspired by this success, we investigate the application of self-attention networks to 3D point cloud processing. We design self-attention layers for point clouds and use these to construct self-attention networks for tasks such as semantic scene segmentation, object part segmentation, and object classification. Our Point Transformer design improves upon prior work across domains and tasks. For example, on the challenging S3DIS dataset for large-scale semantic scene segmentation, the Point Transformer attains an mIoU of 70.4% on Area 5, outperforming the strongest prior model by 3.3 absolute percentage points and crossing the 70% mIoU threshold for the first time.
Code (24)
Tasks
3D Part Segmentation3D Point Cloud Classification3D Semantic SegmentationGeneral Classificationimage-classificationImage ClassificationObjectObject DetectionPoint Cloud SegmentationScene SegmentationSegmentationSemantic SegmentationMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Point Transformer
In this work, we present Point Transformer, a deep neural network that operates directly on unordered and unstructured point sets. We design Point Transformer to extract local and global features and relate both represen…
3D Object Classification3D Part Segmentation3D Point Cloud ClassificationSemantic SegmentationNoiseTrans: Point Cloud Denoising with Transformers
Point clouds obtained from capture devices or 3D reconstruction techniques are often noisy and interfere with downstream tasks. The paper aims to recover the underlying surface of noisy point clouds. We design a novel mo…
3D ReconstructionDenoisingPix4Point: Image Pretrained Standard Transformers for 3D Point Cloud Understanding
While Transformers have achieved impressive success in natural language processing and computer vision, their performance on 3D point clouds is relatively poor. This is mainly due to the limitation of Transformers: a dem…
3D Point Cloud ClassificationInductive BiasPoint Cloud ClassificationSemantic SegmentationPVTransformer: Point-to-Voxel Transformer for Scalable 3D Object Detection
3D object detectors for point clouds often rely on a pooling-based PointNet to encode sparse points into grid-like voxels or pillars. In this paper, we identify that the common PointNet design introduces an information b…
3D Object DetectionObjectobject-detectionObject DetectionDAPoinTr: Domain Adaptive Point Transformer for Point Cloud Completion
Point Transformers (PoinTr) have shown great potential in point cloud completion recently. Nevertheless, effective domain adaptation that improves transferability toward target domains remains unexplored. In this paper, …
DecoderDomain AdaptationPoint Cloud CompletionPseudo Label