Learning Scene Flow in 3D Point Clouds with Noisy Pseudo Labels
- URL: http://arxiv.org/abs/2203.12655v1
- Date: Wed, 23 Mar 2022 18:20:03 GMT
- Title: Learning Scene Flow in 3D Point Clouds with Noisy Pseudo Labels
- Authors: Bing Li, Cheng Zheng, Guohao Li, Bernard Ghanem
- Abstract summary: We propose a novel scene flow method that captures 3D motions from point clouds without relying on ground-truth scene flow annotations.
Our method not only outperforms state-of-the-art self-supervised approaches, but also outperforms some supervised approaches that use accurate ground-truth flows.
- Score: 71.11151016581806
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: We propose a novel scene flow method that captures 3D motions from point
clouds without relying on ground-truth scene flow annotations. Due to the
irregularity and sparsity of point clouds, it is expensive and time-consuming
to acquire ground-truth scene flow annotations. Some state-of-the-art
approaches train scene flow networks in a self-supervised learning manner via
approximating pseudo scene flow labels from point clouds. However, these
methods fail to achieve the performance level of fully supervised methods, due
to the limitations of point cloud such as sparsity and lacking color
information. To provide an alternative, we propose a novel approach that
utilizes monocular RGB images and point clouds to generate pseudo scene flow
labels for training scene flow networks. Our pseudo label generation module
infers pseudo scene labels for point clouds by jointly leveraging rich
appearance information in monocular images and geometric information of point
clouds. To further reduce the negative effect of noisy pseudo labels on the
training, we propose a noisy-label-aware training scheme by exploiting the
geometric relations of points. Experiment results show that our method not only
outperforms state-of-the-art self-supervised approaches, but also outperforms
some supervised approaches that use accurate ground-truth flows.
Related papers
- Self-Supervised 3D Scene Flow Estimation and Motion Prediction using
Local Rigidity Prior [100.98123802027847]
We investigate self-supervised 3D scene flow estimation and class-agnostic motion prediction on point clouds.
We generate pseudo scene flow labels for self-supervised learning through piecewise rigid motion estimation.
Our method achieves new state-of-the-art performance in self-supervised scene flow learning.
arXiv Detail & Related papers (2023-10-17T14:06:55Z) - Data Augmentation-free Unsupervised Learning for 3D Point Cloud
Understanding [61.30276576646909]
We propose an augmentation-free unsupervised approach for point clouds to learn transferable point-level features via soft clustering, named SoftClu.
We exploit the affiliation of points to their clusters as a proxy to enable self-training through a pseudo-label prediction task.
arXiv Detail & Related papers (2022-10-06T10:18:16Z) - 3D Scene Flow Estimation on Pseudo-LiDAR: Bridging the Gap on Estimating
Point Motion [19.419030878019974]
3D scene flow characterizes how the points at the current time flow to the next time in the 3D Euclidean space.
The stability of the predicted scene flow is improved by introducing the dense nature of 2D pixels into the 3D space.
Disparity consistency loss is proposed to achieve more effective unsupervised learning of 3D scene flow.
arXiv Detail & Related papers (2022-09-27T03:27:09Z) - Unsupervised Learning of 3D Scene Flow with 3D Odometry Assistance [20.735976558587588]
Scene flow estimation is used in various applications such as autonomous driving fields, activity recognition, and virtual reality fields.
It is challenging to annotate scene flow with ground truth for real-world data.
We propose to use odometry information to assist the unsupervised learning of scene flow and use real-world LiDAR data to train our network.
arXiv Detail & Related papers (2022-09-11T21:53:43Z) - RCP: Recurrent Closest Point for Scene Flow Estimation on 3D Point
Clouds [44.034836961967144]
3D motion estimation including scene flow and point cloud registration has drawn increasing interest.
Recent methods employ deep neural networks to construct the cost volume for estimating accurate 3D flow.
We decompose the problem into two interlaced stages, where the 3D flows are optimized point-wisely at the first stage and then globally regularized in a recurrent network at the second stage.
arXiv Detail & Related papers (2022-05-23T04:04:30Z) - Self-Point-Flow: Self-Supervised Scene Flow Estimation from Point Clouds
with Optimal Transport and Random Walk [59.87525177207915]
We develop a self-supervised method to establish correspondences between two point clouds to approximate scene flow.
Our method achieves state-of-the-art performance among self-supervised learning methods.
arXiv Detail & Related papers (2021-05-18T03:12:42Z) - SCTN: Sparse Convolution-Transformer Network for Scene Flow Estimation [71.2856098776959]
Estimating 3D motions for point clouds is challenging, since a point cloud is unordered and its density is significantly non-uniform.
We propose a novel architecture named Sparse Convolution-Transformer Network (SCTN) that equips the sparse convolution with the transformer.
We show that the learned relation-based contextual information is rich and helpful for matching corresponding points, benefiting scene flow estimation.
arXiv Detail & Related papers (2021-05-10T15:16:14Z) - Adversarial Self-Supervised Scene Flow Estimation [15.278302535191866]
This work proposes a metric learning approach for self-supervised scene flow estimation.
We outline a benchmark for self-supervised scene flow estimation: the Scene Flow Sandbox.
arXiv Detail & Related papers (2020-11-01T16:37:37Z) - Scene Flow from Point Clouds with or without Learning [47.03163552693887]
Scene flow is the three-dimensional (3D) motion field of a scene.
Current learning-based approaches seek to estimate the scene flow directly from point clouds.
We present a simple and interpretable objective function to recover the scene flow from point clouds.
arXiv Detail & Related papers (2020-10-31T17:24:48Z)
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.