Papers Supervised Only 3D Point Cloud Classification
“Supervised Only 3D Point Cloud Classification” 태그가 달린 논문 13편 · 필터 해제
Mamba3D: Enhancing Local Features for 3D Point Cloud Analysis via State Space Model
Existing Transformer-based models for point cloud analysis suffer from quadratic complexity, leading to compromised point cloud resolution and information loss. In contrast, the newly proposed Mamba model, based on state…
3D Point Cloud ClassificationMambaState Space ModelsSupervised Only 3D Point Cloud ClassificationPoint Cloud Mamba: Point Cloud Learning via State Space Model
Recently, state space models have exhibited strong global modeling capabilities and linear computational complexity in contrast to transformers. This research focuses on applying such architecture to more efficiently and…
MambaState Space ModelsSupervised Only 3D Point Cloud ClassificationDecoupled Local Aggregation for Point Cloud Learning
The unstructured nature of point clouds demands that local aggregation be adaptive to different local structures. Previous methods meet this by explicitly embedding spatial relations into each aggregation process. Althou…
3D Point Cloud ClassificationSemantic SegmentationSupervised Only 3D Point Cloud ClassificationSelf-positioning Point-based Transformer for Point Cloud Understanding
Transformers have shown superior performance on various computer vision tasks with their capabilities to capture long-range dependencies. Despite the success, it is challenging to directly apply Transformers on point clo…
3D Part Segmentation3D Point Cloud ClassificationScene SegmentationSemantic Segmentation+1Parameter is Not All You Need: Starting from Non-Parametric Networks for 3D Point Cloud Analysis
We present a Non-parametric Network for 3D point cloud analysis, Point-NN, which consists of purely non-learnable components: farthest point sampling (FPS), k-nearest neighbors (k-NN), and pooling operations, with trigon…
3D Point Cloud ClassificationAllSupervised Only 3D Point Cloud ClassificationTraining-free 3D Part Segmentation+1Point Cloud Classification Using Content-based Transformer via Clustering in Feature Space
Recently, there have been some attempts of Transformer in 3D point cloud classification. In order to reduce computations, most existing methods focus on local spatial attention, but ignore their content and fail to estab…
3D Point Cloud ClassificationClassificationClusteringPoint Cloud Classification+1PointNeXt: Revisiting PointNet++ with Improved Training and Scaling Strategies
PointNet++ is one of the most influential neural architectures for point cloud understanding. Although the accuracy of PointNet++ has been largely surpassed by recent networks such as PointMLP and Point Transformer, we f…
3D Classification3D Part Segmentation3D Point Cloud Classification3D Semantic Segmentation+3Surface Representation for Point Clouds
Most prior work represents the shapes of point clouds by coordinates. However, it is insufficient to describe the local geometry directly. In this paper, we present \textbf{RepSurf} (representative surfaces), a novel rep…
3D Object Detection3D Point Cloud Classification3D Semantic SegmentationSemantic Segmentation+2Rethinking Network Design and Local Geometry in Point Cloud: A Simple Residual MLP Framework
Point cloud analysis is challenging due to irregularity and unordered data structure. To capture the 3D geometries, prior works mainly rely on exploring sophisticated local geometric extractors using convolution, graph, …
3D Point Cloud ClassificationPoint Cloud SegmentationSupervised Only 3D Point Cloud ClassificationDynamic Graph CNN for Learning on Point Clouds
Point clouds provide a flexible geometric representation suitable for countless applications in computer graphics; they also comprise the raw output of most 3D data acquisition devices. While hand-designed features on po…
3D Part Segmentation3D Point Cloud Classification3D Semantic SegmentationFew-Shot 3D Point Cloud Classification+4Attention Is All You Need
The dominant sequence transduction models are based on complex recurrent or convolutional neural networks in an encoder-decoder configuration. The best performing models also connect the encoder and decoder through an at…
Abstractive Text SummarizationAllCoreference ResolutionDecoder+12PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space
Few prior works study deep learning on point sets. PointNet by Qi et al. is a pioneer in this direction. However, by design PointNet does not capture local structures induced by the metric space points live in, limiting …
3D Part Segmentation3D Point Cloud Classification3D Semantic Segmentation+5PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation
Point cloud is an important type of geometric data structure. Due to its irregular format, most researchers transform such data to regular 3D voxel grids or collections of images. This, however, renders data unnecessaril…
3D Face Reconstruction3D Semantic SegmentationFew-Shot 3D Point Cloud ClassificationPoint Cloud Segmentation+5