FINet: Dual Branches Feature Interaction for Partial-to-Partial Point Cloud Registration

• URL: http://arxiv.org/abs/2106.03479v1
• Date: Mon, 7 Jun 2021 10:15:02 GMT
• Title: FINet: Dual Branches Feature Interaction for Partial-to-Partial Point Cloud Registration
• Authors: Hao Xu, Nianjin Ye, Shuaicheng Liu, Guanghui Liu, Bing Zeng
• Abstract summary: We present FINet, a feature interaction-based structure with the capability to enable and strengthen the information associating between the inputs at multiple stages. Experiments demonstrate that our method performs higher precision and robustness compared to the state-of-the-art traditional and learning-based methods.
• Score: 31.014309817116175
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Data association is important in the point cloud registration. In this work, we propose to solve the partial-to-partial registration from a new perspective, by introducing feature interactions between the source and the reference clouds at the feature extraction stage, such that the registration can be realized without the explicit mask estimation or attentions for the overlapping detection as adopted previously. Specifically, we present FINet, a feature interaction-based structure with the capability to enable and strengthen the information associating between the inputs at multiple stages. To achieve this, we first split the features into two components, one for the rotation and one for the translation, based on the fact that they belong to different solution spaces, yielding a dual branches structure. Second, we insert several interaction modules at the feature extractor for the data association. Third, we propose a transformation sensitivity loss to obtain rotation-attentive and translation-attentive features. Experiments demonstrate that our method performs higher precision and robustness compared to the state-of-the-art traditional and learning-based methods.

Related papers

• DiffVein: A Unified Diffusion Network for Finger Vein Segmentation and Authentication [50.017055360261665]
  We introduce DiffVein, a unified diffusion model-based framework which simultaneously addresses vein segmentation and authentication tasks. For better feature interaction between these two branches, we introduce two specialized modules. In this way, our framework allows for a dynamic interplay between diffusion and segmentation embeddings.
  arXiv  Detail & Related papers  (2024-02-03T06:49:42Z)
• DBDNet:Partial-to-Partial Point Cloud Registration with Dual Branches Decoupling [15.382633946370978]
  We propose an effective registration method with dual branches decoupling for partial-to-partial registration, dubbed as DBDNet. We present an overlap predictor that benefits from explicit feature interaction, which is achieved by the powerful attention mechanism to accurately predict pointwise masks. We design a multi-resolution feature extraction network to capture both local and global patterns thus enhancing both overlap prediction and registration module.
  arXiv  Detail & Related papers  (2023-10-18T06:09:12Z)
• OAAFormer: Robust and Efficient Point Cloud Registration Through Overlapping-Aware Attention in Transformer [37.41780280364752]
  coarse-to-fine feature matching paradigm has received substantial attention in the domain of point cloud registration. We introduce a soft matching mechanism, facilitating the propagation of potentially valuable correspondences from coarse to fine levels. Our approach leads to a substantial increase of about 7% in the inlier ratio, as well as an enhancement of 2-4% in registration recall.
  arXiv  Detail & Related papers  (2023-10-15T12:27:18Z)
• Discriminative Co-Saliency and Background Mining Transformer for Co-Salient Object Detection [111.04994415248736]
  We propose a Discriminative co-saliency and background Mining Transformer framework (DMT) We use two types of pre-defined tokens to mine co-saliency and background information via our proposed contrast-induced pixel-to-token correlation and co-saliency token-to-token correlation modules. Experimental results on three benchmark datasets demonstrate the effectiveness of our proposed method.
  arXiv  Detail & Related papers  (2023-04-30T15:56:47Z)
• Part-guided Relational Transformers for Fine-grained Visual Recognition [59.20531172172135]
  We propose a framework to learn the discriminative part features and explore correlations with a feature transformation module. Our proposed approach does not rely on additional part branches and reaches state-the-of-art performance on 3-of-the-level object recognition.
  arXiv  Detail & Related papers  (2022-12-28T03:45:56Z)
• Disentangled Representation Learning for Text-Video Retrieval [51.861423831566626]
  Cross-modality interaction is a critical component in Text-Video Retrieval (TVR) We study the interaction paradigm in depth, where we find that its computation can be split into two terms. We propose a disentangled framework to capture a sequential and hierarchical representation.
  arXiv  Detail & Related papers  (2022-03-14T13:55:33Z)
• GaitStrip: Gait Recognition via Effective Strip-based Feature Representations and Multi-Level Framework [34.397404430838286]
  We present a strip-based multi-level gait recognition network, named GaitStrip, to extract comprehensive gait information at different levels. To be specific, our high-level branch explores the context of gait sequences and our low-level one focuses on detailed posture changes. Our GaitStrip achieves state-of-the-art performance in both normal walking and complex conditions.
  arXiv  Detail & Related papers  (2022-03-08T09:49:48Z)
• Consistent Two-Flow Network for Tele-Registration of Point Clouds [74.51029406361997]
  We present a learning-based technique that allows registration between point clouds, presented in arbitrary poses, and having little or even no overlap. Our technique is based on a novel neural network design that learns a prior of a class of shapes and can complete a partial shape. We show that, compared with each separate flow, this two-flow training leads to robust and reliable tele-registration.
  arXiv  Detail & Related papers  (2021-06-01T09:03:21Z)
• Interactive Fusion of Multi-level Features for Compositional Activity Recognition [100.75045558068874]
  We present a novel framework that accomplishes this goal by interactive fusion. We implement the framework in three steps, namely, positional-to-appearance feature extraction, semantic feature interaction, and semantic-to-positional prediction. We evaluate our approach on two action recognition datasets, Something-Something and Charades.
  arXiv  Detail & Related papers  (2020-12-10T14:17:18Z)
• Bi-Directional Attention for Joint Instance and Semantic Segmentation in Point Clouds [9.434847591440485]
  We build a Bi-Directional Attention module on backbone neural networks for 3D point cloud perception. It uses similarity matrix measured from features for one task to help aggregate non-local information for the other task. From comprehensive experiments and ablation studies on the S3DIS dataset and the PartNet dataset, the superiority of our method is verified.
  arXiv  Detail & Related papers  (2020-03-11T17:16:07Z)

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.