TransPose: 6D Object Pose Estimation with Geometry-Aware Transformer
- URL: http://arxiv.org/abs/2310.16279v3
- Date: Tue, 23 Apr 2024 03:54:27 GMT
- Title: TransPose: 6D Object Pose Estimation with Geometry-Aware Transformer
- Authors: Xiao Lin, Deming Wang, Guangliang Zhou, Chengju Liu, Qijun Chen,
- Abstract summary: TransPose is a novel 6D pose framework that exploits Transformer with geometry-aware module to develop better learning of point cloud feature representations.
TransPose achieves competitive results on three benchmark datasets.
- Score: 16.674933679692728
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: Estimating the 6D object pose is an essential task in many applications. Due to the lack of depth information, existing RGB-based methods are sensitive to occlusion and illumination changes. How to extract and utilize the geometry features in depth information is crucial to achieve accurate predictions. To this end, we propose TransPose, a novel 6D pose framework that exploits Transformer Encoder with geometry-aware module to develop better learning of point cloud feature representations. Specifically, we first uniformly sample point cloud and extract local geometry features with the designed local feature extractor base on graph convolution network. To improve robustness to occlusion, we adopt Transformer to perform the exchange of global information, making each local feature contains global information. Finally, we introduce geometry-aware module in Transformer Encoder, which to form an effective constrain for point cloud feature learning and makes the global information exchange more tightly coupled with point cloud tasks. Extensive experiments indicate the effectiveness of TransPose, our pose estimation pipeline achieves competitive results on three benchmark datasets.
Related papers
- 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) - AGO-Net: Association-Guided 3D Point Cloud Object Detection Network [86.10213302724085]
We propose a novel 3D detection framework that associates intact features for objects via domain adaptation.
We achieve new state-of-the-art performance on the KITTI 3D detection benchmark in both accuracy and speed.
arXiv Detail & Related papers (2022-08-24T16:54:38Z) - 3DCTN: 3D Convolution-Transformer Network for Point Cloud Classification [23.0009969537045]
This paper presents a novel hierarchical framework that incorporates convolution with Transformer for point cloud classification.
Our method achieves state-of-the-art classification performance, in terms of both accuracy and efficiency.
arXiv Detail & Related papers (2022-03-02T02:42:14Z) - Full Transformer Framework for Robust Point Cloud Registration with Deep
Information Interaction [9.431484068349903]
Recent Transformer-based methods have achieved advanced performance in point cloud registration.
Recent CNNs fail to model global relations due to their local fields receptive.
shallow-wide architecture of Transformers and lack of positional encoding lead to indistinct feature extraction.
arXiv Detail & Related papers (2021-12-17T08:40:52Z) - Geometry-Contrastive Transformer for Generalized 3D Pose Transfer [95.56457218144983]
The intuition of this work is to perceive the geometric inconsistency between the given meshes with the powerful self-attention mechanism.
We propose a novel geometry-contrastive Transformer that has an efficient 3D structured perceiving ability to the global geometric inconsistencies.
We present a latent isometric regularization module together with a novel semi-synthesized dataset for the cross-dataset 3D pose transfer task.
arXiv Detail & Related papers (2021-12-14T13:14:24Z) - 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) - 6D-ViT: Category-Level 6D Object Pose Estimation via Transformer-based
Instance Representation Learning [0.0]
6D-ViT is a transformer-based instance representation learning network.
It is suitable for highly accurate category-level object pose estimation on RGB-D images.
arXiv Detail & Related papers (2021-10-10T13:34:16Z) - 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) - FS-Net: Fast Shape-based Network for Category-Level 6D Object Pose
Estimation with Decoupled Rotation Mechanism [49.89268018642999]
We propose a fast shape-based network (FS-Net) with efficient category-level feature extraction for 6D pose estimation.
The proposed method achieves state-of-the-art performance in both category- and instance-level 6D object pose estimation.
arXiv Detail & Related papers (2021-03-12T03:07:24Z) - 3D Object Detection with Pointformer [29.935891419574602]
We propose Pointformer, a Transformer backbone designed for 3D point clouds to learn features effectively.
A Local Transformer module is employed to model interactions among points in a local region, which learns context-dependent region features at an object level.
A Global Transformer is designed to learn context-aware representations at the scene level.
arXiv Detail & Related papers (2020-12-21T15:12:54Z)
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.