SimIPU: Simple 2D Image and 3D Point Cloud Unsupervised Pre-Training for Spatial-Aware Visual Representations

• URL: http://arxiv.org/abs/2112.04680v1
• Date: Thu, 9 Dec 2021 03:27:00 GMT
• Title: SimIPU: Simple 2D Image and 3D Point Cloud Unsupervised Pre-Training for Spatial-Aware Visual Representations
• Authors: Zhenyu Li, Zehui Chen, Ang Li, Liangji Fang, Qinhong Jiang, Xianming Liu, Junjun Jiang, Bolei Zhou, Hang Zhao
• Abstract summary: We propose a 2D Image and 3D Point cloud Unsupervised pre-training strategy, called SimIPU. Specifically, we develop a multi-modal contrastive learning framework that consists of an intra-modal spatial perception module and an inter-modal feature interaction module. To the best of our knowledge, this is the first study to explore contrastive learning pre-training strategies for outdoor multi-modal datasets.
• Score: 85.38562724999898
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Pre-training has become a standard paradigm in many computer vision tasks. However, most of the methods are generally designed on the RGB image domain. Due to the discrepancy between the two-dimensional image plane and the three-dimensional space, such pre-trained models fail to perceive spatial information and serve as sub-optimal solutions for 3D-related tasks. To bridge this gap, we aim to learn a spatial-aware visual representation that can describe the three-dimensional space and is more suitable and effective for these tasks. To leverage point clouds, which are much more superior in providing spatial information compared to images, we propose a simple yet effective 2D Image and 3D Point cloud Unsupervised pre-training strategy, called SimIPU. Specifically, we develop a multi-modal contrastive learning framework that consists of an intra-modal spatial perception module to learn a spatial-aware representation from point clouds and an inter-modal feature interaction module to transfer the capability of perceiving spatial information from the point cloud encoder to the image encoder, respectively. Positive pairs for contrastive losses are established by the matching algorithm and the projection matrix. The whole framework is trained in an unsupervised end-to-end fashion. To the best of our knowledge, this is the first study to explore contrastive learning pre-training strategies for outdoor multi-modal datasets, containing paired camera images and LIDAR point clouds. Codes and models are available at https://github.com/zhyever/SimIPU.

Related papers

• ImOV3D: Learning Open-Vocabulary Point Clouds 3D Object Detection from Only 2D Images [19.02348585677397]
  Open-vocabulary 3D object detection (OV-3Det) aims to generalize beyond the limited number of base categories labeled during the training phase. The biggest bottleneck is the scarcity of annotated 3D data, whereas 2D image datasets are abundant and richly annotated. We propose a novel framework ImOV3D to leverage pseudo multimodal representation containing both images and point clouds (PC) to close the modality gap.
  arXiv  Detail & Related papers  (2024-10-31T15:02:05Z)
• HVDistill: Transferring Knowledge from Images to Point Clouds via Unsupervised Hybrid-View Distillation [106.09886920774002]
  We present a hybrid-view-based knowledge distillation framework, termed HVDistill, to guide the feature learning of a point cloud neural network. Our method achieves consistent improvements over the baseline trained from scratch and significantly out- performs the existing schemes.
  arXiv  Detail & Related papers  (2024-03-18T14:18:08Z)
• Self-supervised Learning of LiDAR 3D Point Clouds via 2D-3D Neural Calibration [107.61458720202984]
  This paper introduces a novel self-supervised learning framework for enhancing 3D perception in autonomous driving scenes. We propose the learnable transformation alignment to bridge the domain gap between image and point cloud data. We establish dense 2D-3D correspondences to estimate the rigid pose.
  arXiv  Detail & Related papers  (2024-01-23T02:41:06Z)
• Leveraging Large-Scale Pretrained Vision Foundation Models for Label-Efficient 3D Point Cloud Segmentation [67.07112533415116]
  We present a novel framework that adapts various foundational models for the 3D point cloud segmentation task. Our approach involves making initial predictions of 2D semantic masks using different large vision models. To generate robust 3D semantic pseudo labels, we introduce a semantic label fusion strategy that effectively combines all the results via voting.
  arXiv  Detail & Related papers  (2023-11-03T15:41:15Z)
• Cross-Modal Information-Guided Network using Contrastive Learning for Point Cloud Registration [17.420425069785946]
  We present a novel Cross-Modal Information-Guided Network (CMIGNet) for point cloud registration. We first incorporate the projected images from the point clouds and fuse the cross-modal features using the attention mechanism. We employ two contrastive learning strategies, namely overlapping contrastive learning and cross-modal contrastive learning.
  arXiv  Detail & Related papers  (2023-11-02T12:56:47Z)
• CLIP$^2$: Contrastive Language-Image-Point Pretraining from Real-World Point Cloud Data [80.42480679542697]
  We propose Contrastive Language-Image-Point Cloud Pretraining (CLIP$2$) to learn the transferable 3D point cloud representation in realistic scenarios. Specifically, we exploit naturally-existed correspondences in 2D and 3D scenarios, and build well-aligned and instance-based text-image-point proxies from those complex scenarios.
  arXiv  Detail & Related papers  (2023-03-22T09:32:45Z)
• CrossPoint: Self-Supervised Cross-Modal Contrastive Learning for 3D Point Cloud Understanding [2.8661021832561757]
  CrossPoint is a simple cross-modal contrastive learning approach to learn transferable 3D point cloud representations. Our approach outperforms the previous unsupervised learning methods on a diverse range of downstream tasks including 3D object classification and segmentation.
  arXiv  Detail & Related papers  (2022-03-01T18:59:01Z)
• Unsupervised Learning of Visual 3D Keypoints for Control [104.92063943162896]
  Learning sensorimotor control policies from high-dimensional images crucially relies on the quality of the underlying visual representations. We propose a framework to learn such a 3D geometric structure directly from images in an end-to-end unsupervised manner. These discovered 3D keypoints tend to meaningfully capture robot joints as well as object movements in a consistent manner across both time and 3D space.
  arXiv  Detail & Related papers  (2021-06-14T17:59:59Z)

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.