REVIEW 5 cited by
Transformers in 3D Point Clouds: A Survey
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
Signed reviews
read the original abstract
Transformers have been at the heart of the Natural Language Processing (NLP) and Computer Vision (CV) revolutions. The significant success in NLP and CV inspired exploring the use of Transformers in point cloud processing. However, how do Transformers cope with the irregularity and unordered nature of point clouds? How suitable are Transformers for different 3D representations (e.g., point- or voxel-based)? How competent are Transformers for various 3D processing tasks? As of now, there is still no systematic survey of the research on these issues. For the first time, we provided a comprehensive overview of increasingly popular Transformers for 3D point cloud analysis. We start by introducing the theory of the Transformer architecture and reviewing its applications in 2D/3D fields. Then, we present three different taxonomies (i.e., implementation-, data representation-, and task-based), which can classify current Transformer-based methods from multiple perspectives. Furthermore, we present the results of an investigation of the variants and improvements of the self-attention mechanism in 3D. To demonstrate the superiority of Transformers in point cloud analysis, we present comprehensive comparisons of various Transformer-based methods for classification, segmentation, and object detection. Finally, we suggest three potential research directions, providing benefit references for the development of 3D Transformers.
Forward citations
Cited by 5 Pith papers
-
EuLearn: A 3D database for learning Euler characteristics
EuLearn is a benchmark of 3,300 embedded surfaces with uniformly distributed genus (0 to 10), plus a graph-sampling method and adjacency-aware PointNet and Transformer variants that reach about 0.8 genus-classificatio...
-
ECO: Incremental Ego-Centric Octree Update for Point Streams
Ego-Centric Octree (ECO) maintains a robot-centered, fixed-volume octree via shift-out/shift-in/overlap incremental updates, reducing update time ~25% vs full rebuild and ~55% vs bounded i-Octree on KITTI.
-
Part Segmentation of Human Meshes via Multi-View Human Parsing
A multi-view 2D human parsing backprojection pipeline generates pseudo-ground-truth labels for THuman2.1 meshes, and a PointTransformer trained on geometry alone reaches up to 74.4 mIoU when measured against those pse...
-
Foundational Models for 3D Point Clouds: A Survey and Outlook
A structured review of methods that build or adapt 2D foundation models and LLMs for 3D point cloud tasks, with a proposed taxonomy and curated paper list.
-
Relational inductive biases on attention mechanisms
Attention mechanisms are classified by their relational inductive bias: self-attention assumes a complete graph, masked attention a total order, strided attention p-previous connections, encoder-decoder a bipartite gr...
Discussion (0). Continue with ORCID to comment.