3DMambaComplete: Exploring Structured State Space Model for Point Cloud Completion

• URL: http://arxiv.org/abs/2404.07106v1
• Date: Wed, 10 Apr 2024 15:45:03 GMT
• Title: 3DMambaComplete: Exploring Structured State Space Model for Point Cloud Completion
• Authors: Yixuan Li, Weidong Yang, Ben Fei,
• Abstract summary: 3DMambaComplete is a point cloud completion network built on the novel Mamba framework. It encodes point cloud features using Mamba's selection mechanism and predicts a set of Hyperpoints. A deformation method transforms the 2D mesh representation of HyperPoints into a fine-grained 3D structure for point cloud reconstruction.
• Score: 19.60626235337542
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Point cloud completion aims to generate a complete and high-fidelity point cloud from an initially incomplete and low-quality input. A prevalent strategy involves leveraging Transformer-based models to encode global features and facilitate the reconstruction process. However, the adoption of pooling operations to obtain global feature representations often results in the loss of local details within the point cloud. Moreover, the attention mechanism inherent in Transformers introduces additional computational complexity, rendering it challenging to handle long sequences effectively. To address these issues, we propose 3DMambaComplete, a point cloud completion network built on the novel Mamba framework. It comprises three modules: HyperPoint Generation encodes point cloud features using Mamba's selection mechanism and predicts a set of Hyperpoints. A specific offset is estimated, and the down-sampled points become HyperPoints. The HyperPoint Spread module disperses these HyperPoints across different spatial locations to avoid concentration. Finally, a deformation method transforms the 2D mesh representation of HyperPoints into a fine-grained 3D structure for point cloud reconstruction. Extensive experiments conducted on various established benchmarks demonstrate that 3DMambaComplete surpasses state-of-the-art point cloud completion methods, as confirmed by qualitative and quantitative analyses.

Related papers

• Point Cloud Mamba: Point Cloud Learning via State Space Model [73.7454734756626]
  We show that Mamba-based point cloud methods can outperform previous methods based on transformer or multi-layer perceptrons (MLPs) In particular, we demonstrate that Mamba-based point cloud methods can outperform previous methods based on transformer or multi-layer perceptrons (MLPs) Point Cloud Mamba surpasses the state-of-the-art (SOTA) point-based method PointNeXt and achieves new SOTA performance on the ScanNN, ModelNet40, ShapeNetPart, and S3DIS datasets.
  arXiv  Detail & Related papers  (2024-03-01T18:59:03Z)
• SeedFormer: Patch Seeds based Point Cloud Completion with Upsample Transformer [46.800630776714016]
  We propose a novel SeedFormer to improve the ability of detail preservation and recovery in point cloud completion. We introduce a new shape representation, namely Patch Seeds, which not only captures general structures from partial inputs but also preserves regional information of local patterns. Our method outperforms state-of-the-art completion networks on several benchmark datasets.
  arXiv  Detail & Related papers  (2022-07-21T06:15:59Z)
• PMP-Net++: Point Cloud Completion by Transformer-Enhanced Multi-step Point Moving Paths [60.32185890237936]
  We design a novel neural network, named PMP-Net++, to mimic behavior of an earth mover. It moves each point of incomplete input to obtain a complete point cloud, where total distance of point moving paths (PMPs) should be the shortest. The network learns a strict and unique correspondence on point-level, and thus improves quality of predicted complete shape.
  arXiv  Detail & Related papers  (2022-02-19T03:00:40Z)
• A Conditional Point Diffusion-Refinement Paradigm for 3D Point Cloud Completion [69.32451612060214]
  Real-scanned 3D point clouds are often incomplete, and it is important to recover complete point clouds for downstream applications. Most existing point cloud completion methods use Chamfer Distance (CD) loss for training. We propose a novel Point Diffusion-Refinement (PDR) paradigm for point cloud completion.
  arXiv  Detail & Related papers  (2021-12-07T06:59:06Z)
• Deep Point Cloud Reconstruction [74.694733918351]
  Point cloud obtained from 3D scanning is often sparse, noisy, and irregular. To cope with these issues, recent studies have been separately conducted to densify, denoise, and complete inaccurate point cloud. We propose a deep point cloud reconstruction network consisting of two stages: 1) a 3D sparse stacked-hourglass network as for the initial densification and denoising, 2) a refinement via transformers converting the discrete voxels into 3D points.
  arXiv  Detail & Related papers  (2021-11-23T07:53:28Z)
• PoinTr: Diverse Point Cloud Completion with Geometry-Aware Transformers [81.71904691925428]
  We present a new method that reformulates point cloud completion as a set-to-set translation problem. We also design a new model, called PoinTr, that adopts a transformer encoder-decoder architecture for point cloud completion. Our method outperforms state-of-the-art methods by a large margin on both the new benchmarks and the existing ones.
  arXiv  Detail & Related papers  (2021-08-19T17:58:56Z)
• PMP-Net: Point Cloud Completion by Learning Multi-step Point Moving Paths [54.459879603473034]
  We design a novel neural network, named PMP-Net, to mimic the behavior of an earth mover. It moves each point of the incomplete input to complete the point cloud, where the total distance of point moving paths should be shortest. It learns a strict and unique correspondence on point-level, which can capture the detailed topology and structure relationships between the incomplete shape and the complete target.
  arXiv  Detail & Related papers  (2020-12-07T01:34:38Z)

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.