HVDistill: Transferring Knowledge from Images to Point Clouds via Unsupervised Hybrid-View Distillation

• URL: http://arxiv.org/abs/2403.11817v1
• Date: Mon, 18 Mar 2024 14:18:08 GMT
• Title: HVDistill: Transferring Knowledge from Images to Point Clouds via Unsupervised Hybrid-View Distillation
• Authors: Sha Zhang, Jiajun Deng, Lei Bai, Houqiang Li, Wanli Ouyang, Yanyong Zhang,
• Abstract summary: 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.
• Score: 106.09886920774002
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: We present a hybrid-view-based knowledge distillation framework, termed HVDistill, to guide the feature learning of a point cloud neural network with a pre-trained image network in an unsupervised man- ner. By exploiting the geometric relationship between RGB cameras and LiDAR sensors, the correspondence between the two modalities based on both image- plane view and bird-eye view can be established, which facilitates representation learning. Specifically, the image-plane correspondences can be simply ob- tained by projecting the point clouds, while the bird- eye-view correspondences can be achieved by lifting pixels to the 3D space with the predicted depths un- der the supervision of projected point clouds. The image teacher networks provide rich semantics from the image-plane view and meanwhile acquire geometric information from the bird-eye view. Indeed, image features from the two views naturally comple- ment each other and together can ameliorate the learned feature representation of the point cloud stu- dent networks. Moreover, with a self-supervised pre- trained 2D network, HVDistill requires neither 2D nor 3D annotations. We pre-train our model on nuScenes dataset and transfer it to several downstream tasks on nuScenes, SemanticKITTI, and KITTI datasets for evaluation. Extensive experimental results show that our method achieves consistent improvements over the baseline trained from scratch and significantly out- performs the existing schemes. Codes are available at git@github.com:zhangsha1024/HVDistill.git.

Related papers

• 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)
• 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)
• Take-A-Photo: 3D-to-2D Generative Pre-training of Point Cloud Models [97.58685709663287]
  generative pre-training can boost the performance of fundamental models in 2D vision. In 3D vision, the over-reliance on Transformer-based backbones and the unordered nature of point clouds have restricted the further development of generative pre-training. We propose a novel 3D-to-2D generative pre-training method that is adaptable to any point cloud model.
  arXiv  Detail & Related papers  (2023-07-27T16:07:03Z)
• Ponder: Point Cloud Pre-training via Neural Rendering [93.34522605321514]
  We propose a novel approach to self-supervised learning of point cloud representations by differentiable neural encoders. The learned point-cloud can be easily integrated into various downstream tasks, including not only high-level rendering tasks like 3D detection and segmentation, but low-level tasks like 3D reconstruction and image rendering.
  arXiv  Detail & Related papers  (2022-12-31T08:58:39Z)
• PointVST: Self-Supervised Pre-training for 3D Point Clouds via View-Specific Point-to-Image Translation [64.858505571083]
  This paper proposes a translative pre-training framework, namely PointVST. It is driven by a novel self-supervised pretext task of cross-modal translation from 3D point clouds to their corresponding diverse forms of 2D rendered images.
  arXiv  Detail & Related papers  (2022-12-29T07:03:29Z)
• 3D Point Cloud Pre-training with Knowledge Distillation from 2D Images [128.40422211090078]
  We propose a knowledge distillation method for 3D point cloud pre-trained models to acquire knowledge directly from the 2D representation learning model. Specifically, we introduce a cross-attention mechanism to extract concept features from 3D point cloud and compare them with the semantic information from 2D images. In this scheme, the point cloud pre-trained models learn directly from rich information contained in 2D teacher models.
  arXiv  Detail & Related papers  (2022-12-17T23:21:04Z)
• 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)

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.