PoinTr: Diverse Point Cloud Completion with Geometry-Aware Transformers
- URL: http://arxiv.org/abs/2108.08839v1
- Date: Thu, 19 Aug 2021 17:58:56 GMT
- Title: PoinTr: Diverse Point Cloud Completion with Geometry-Aware Transformers
- Authors: Xumin Yu, Yongming Rao, Ziyi Wang, Zuyan Liu, Jiwen Lu, Jie Zhou
- Abstract summary: 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.
- Score: 81.71904691925428
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Point clouds captured in real-world applications are often incomplete due to
the limited sensor resolution, single viewpoint, and occlusion. Therefore,
recovering the complete point clouds from partial ones becomes an indispensable
task in many practical applications. In this paper, we present a new method
that reformulates point cloud completion as a set-to-set translation problem
and design a new model, called PoinTr that adopts a transformer encoder-decoder
architecture for point cloud completion. By representing the point cloud as a
set of unordered groups of points with position embeddings, we convert the
point cloud to a sequence of point proxies and employ the transformers for
point cloud generation. To facilitate transformers to better leverage the
inductive bias about 3D geometric structures of point clouds, we further devise
a geometry-aware block that models the local geometric relationships
explicitly. The migration of transformers enables our model to better learn
structural knowledge and preserve detailed information for point cloud
completion. Furthermore, we propose two more challenging benchmarks with more
diverse incomplete point clouds that can better reflect the real-world
scenarios to promote future research. Experimental results show that our method
outperforms state-of-the-art methods by a large margin on both the new
benchmarks and the existing ones. Code is available at
https://github.com/yuxumin/PoinTr
Related papers
- Patch-Wise Point Cloud Generation: A Divide-and-Conquer Approach [83.05340155068721]
We devise a new 3d point cloud generation framework using a divide-and-conquer approach.
All patch generators are based on learnable priors, which aim to capture the information of geometry primitives.
Experimental results on a variety of object categories from the most popular point cloud dataset, ShapeNet, show the effectiveness of the proposed patch-wise point cloud generation.
arXiv Detail & Related papers (2023-07-22T11:10:39Z) - NoiseTrans: Point Cloud Denoising with Transformers [4.143032261649984]
We design a novel model, NoiseTrans, which uses transformer encoder architecture for point cloud denoising.
We obtain structural similarity of point-based point clouds with the assistance of the transformer's core self-attention mechanism.
Experiments show that our model outperforms state-of-the-art methods in various datasets and noise environments.
arXiv Detail & Related papers (2023-04-24T04:01:23Z) - AdaPoinTr: Diverse Point Cloud Completion with Adaptive Geometry-Aware
Transformers [94.11915008006483]
We present a new method that reformulates point cloud completion as a set-to-set translation problem.
We design a new model, called PoinTr, which adopts a Transformer encoder-decoder architecture for point cloud completion.
Our method attains 6.53 CD on PCN, 0.81 CD on ShapeNet-55 and 0.392 MMD on real-world KITTI.
arXiv Detail & Related papers (2023-01-11T16:14:12Z) - 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) - CompleteDT: Point Cloud Completion with Dense Augment Inference
Transformers [14.823742295692856]
Point cloud completion task aims to predict the missing part of incomplete point clouds and generate point clouds with details.
We propose a novel point cloud completion network, CompleteDT, which is based on the transformer.
arXiv Detail & Related papers (2022-05-30T11:17:31Z) - Point-BERT: Pre-training 3D Point Cloud Transformers with Masked Point
Modeling [104.82953953453503]
We present Point-BERT, a new paradigm for learning Transformers to generalize the concept of BERT to 3D point cloud.
Experiments demonstrate that the proposed BERT-style pre-training strategy significantly improves the performance of standard point cloud Transformers.
arXiv Detail & Related papers (2021-11-29T18:59:03Z) - 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) - GRNet: Gridding Residual Network for Dense Point Cloud Completion [54.43648460932248]
Estimating the complete 3D point cloud from an incomplete one is a key problem in many vision and robotics applications.
We propose a novel Gridding Residual Network (GRNet) for point cloud completion.
Experimental results indicate that the proposed GRNet performs favorably against state-of-the-art methods on the ShapeNet, Completion3D, and KITTI benchmarks.
arXiv Detail & Related papers (2020-06-06T02:46:39Z)
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.