SelfVoxeLO: Self-supervised LiDAR Odometry with Voxel-based Deep Neural
Networks
- URL: http://arxiv.org/abs/2010.09343v3
- Date: Wed, 9 Feb 2022 04:59:30 GMT
- Title: SelfVoxeLO: Self-supervised LiDAR Odometry with Voxel-based Deep Neural
Networks
- Authors: Yan Xu, Zhaoyang Huang, Kwan-Yee Lin, Xinge Zhu, Jianping Shi, Hujun
Bao, Guofeng Zhang, Hongsheng Li
- Abstract summary: We propose a self-supervised LiDAR odometry method, dubbed SelfVoxeLO, to tackle these two difficulties.
Specifically, we propose a 3D convolution network to process the raw LiDAR data directly, which extracts features that better encode the 3D geometric patterns.
We evaluate our method's performances on two large-scale datasets, i.e., KITTI and Apollo-SouthBay.
- Score: 81.64530401885476
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Recent learning-based LiDAR odometry methods have demonstrated their
competitiveness. However, most methods still face two substantial challenges:
1) the 2D projection representation of LiDAR data cannot effectively encode 3D
structures from the point clouds; 2) the needs for a large amount of labeled
data for training limit the application scope of these methods. In this paper,
we propose a self-supervised LiDAR odometry method, dubbed SelfVoxeLO, to
tackle these two difficulties. Specifically, we propose a 3D convolution
network to process the raw LiDAR data directly, which extracts features that
better encode the 3D geometric patterns. To suit our network to self-supervised
learning, we design several novel loss functions that utilize the inherent
properties of LiDAR point clouds. Moreover, an uncertainty-aware mechanism is
incorporated in the loss functions to alleviate the interference of moving
objects/noises. We evaluate our method's performances on two large-scale
datasets, i.e., KITTI and Apollo-SouthBay. Our method outperforms
state-of-the-art unsupervised methods by 27%/32% in terms of
translational/rotational errors on the KITTI dataset and also performs well on
the Apollo-SouthBay dataset. By including more unlabelled training data, our
method can further improve performance comparable to the supervised methods.
Related papers
- FLARES: Fast and Accurate LiDAR Multi-Range Semantic Segmentation [52.89847760590189]
3D scene understanding is a critical yet challenging task in autonomous driving.
Recent methods leverage the range-view representation to improve processing efficiency.
We re-design the workflow for range-view-based LiDAR semantic segmentation.
arXiv Detail & Related papers (2025-02-13T12:39:26Z) - A Lesson in Splats: Teacher-Guided Diffusion for 3D Gaussian Splats Generation with 2D Supervision [65.33043028101471]
We introduce a diffusion model for Gaussian Splats, SplatDiffusion, to enable generation of three-dimensional structures from single images.
Existing methods rely on deterministic, feed-forward predictions, which limit their ability to handle the inherent ambiguity of 3D inference from 2D data.
arXiv Detail & Related papers (2024-12-01T00:29:57Z) - LiOn-XA: Unsupervised Domain Adaptation via LiDAR-Only Cross-Modal Adversarial Training [61.26381389532653]
LiOn-XA is an unsupervised domain adaptation (UDA) approach that combines LiDAR-Only Cross-Modal (X) learning with Adversarial training for 3D LiDAR point cloud semantic segmentation.
Our experiments on 3 real-to-real adaptation scenarios demonstrate the effectiveness of our approach.
arXiv Detail & Related papers (2024-10-21T09:50:17Z) - Approaching Outside: Scaling Unsupervised 3D Object Detection from 2D Scene [22.297964850282177]
We propose LiDAR-2D Self-paced Learning (LiSe) for unsupervised 3D detection.
RGB images serve as a valuable complement to LiDAR data, offering precise 2D localization cues.
Our framework devises a self-paced learning pipeline that incorporates adaptive sampling and weak model aggregation strategies.
arXiv Detail & Related papers (2024-07-11T14:58:49Z) - 4D Contrastive Superflows are Dense 3D Representation Learners [62.433137130087445]
We introduce SuperFlow, a novel framework designed to harness consecutive LiDAR-camera pairs for establishing pretraining objectives.
To further boost learning efficiency, we incorporate a plug-and-play view consistency module that enhances alignment of the knowledge distilled from camera views.
arXiv Detail & Related papers (2024-07-08T17:59:54Z) - Dense Voxel Fusion for 3D Object Detection [10.717415797194896]
Voxel Fusion (DVF) is a sequential fusion method that generates multi-scale dense voxel feature representations.
We train directly with ground truth 2D bounding box labels, avoiding noisy, detector-specific, 2D predictions.
We show that our proposed multi-modal training strategy results in better generalization compared to training using erroneous 2D predictions.
arXiv Detail & Related papers (2022-03-02T04:51:31Z) - Robust Self-Supervised LiDAR Odometry via Representative Structure
Discovery and 3D Inherent Error Modeling [67.75095378830694]
We develop a two-stage odometry estimation network, where we obtain the ego-motion by estimating a set of sub-region transformations.
In this paper, we aim to alleviate the influence of unreliable structures in training, inference and mapping phases.
Our two-frame odometry outperforms the previous state of the arts by 16%/12% in terms of translational/rotational errors.
arXiv Detail & Related papers (2022-02-27T12:52:27Z) - Advancing Self-supervised Monocular Depth Learning with Sparse LiDAR [22.202192422883122]
We propose a novel two-stage network to advance the self-supervised monocular dense depth learning.
Our model fuses monocular image features and sparse LiDAR features to predict initial depth maps.
Our model outperforms the state-of-the-art sparse-LiDAR-based method (Pseudo-LiDAR++) by more than 68% for the downstream task monocular 3D object detection.
arXiv Detail & Related papers (2021-09-20T15:28:36Z) - Scan-based Semantic Segmentation of LiDAR Point Clouds: An Experimental
Study [2.6205925938720833]
State of the art methods use deep neural networks to predict semantic classes for each point in a LiDAR scan.
A powerful and efficient way to process LiDAR measurements is to use two-dimensional, image-like projections.
We demonstrate various techniques to boost the performance and to improve runtime as well as memory constraints.
arXiv Detail & Related papers (2020-04-06T11:08:12Z)
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.