Unsupervised Learning of 3D Scene Flow with 3D Odometry Assistance

• URL: http://arxiv.org/abs/2209.04945v1
• Date: Sun, 11 Sep 2022 21:53:43 GMT
• Title: Unsupervised Learning of 3D Scene Flow with 3D Odometry Assistance
• Authors: Guangming Wang, Zhiheng Feng, Chaokang Jiang, Hesheng Wang
• Abstract summary: 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.
• Score: 20.735976558587588
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Scene flow represents the 3D motion of each point in the scene, which explicitly describes the distance and the direction of each point's movement. Scene flow estimation is used in various applications such as autonomous driving fields, activity recognition, and virtual reality fields. As it is challenging to annotate scene flow with ground truth for real-world data, this leaves no real-world dataset available to provide a large amount of data with ground truth for scene flow estimation. Therefore, many works use synthesized data to pre-train their network and real-world LiDAR data to finetune. Unlike the previous unsupervised learning of scene flow in point clouds, we propose to use odometry information to assist the unsupervised learning of scene flow and use real-world LiDAR data to train our network. Supervised odometry provides more accurate shared cost volume for scene flow. In addition, the proposed network has mask-weighted warp layers to get a more accurate predicted point cloud. The warp operation means applying an estimated pose transformation or scene flow to a source point cloud to obtain a predicted point cloud and is the key to refining scene flow from coarse to fine. When performing warp operations, the points in different states use different weights for the pose transformation and scene flow transformation. We classify the states of points as static, dynamic, and occluded, where the static masks are used to divide static and dynamic points, and the occlusion masks are used to divide occluded points. The mask-weighted warp layer indicates that static masks and occlusion masks are used as weights when performing warp operations. Our designs are proved to be effective in ablation experiments. The experiment results show the promising prospect of an odometry-assisted unsupervised learning method for 3D scene flow in real-world data.

Related papers

• The Drunkard's Odometry: Estimating Camera Motion in Deforming Scenes [79.00228778543553]
  This dataset is the first large set of exploratory camera trajectories with ground truth inside 3D scenes. Simulations in realistic 3D buildings lets us obtain a vast amount of data and ground truth labels. We present a novel deformable odometry method, dubbed the Drunkard's Odometry, which decomposes optical flow estimates into rigid-body camera motion.
  arXiv  Detail & Related papers  (2023-06-29T13:09:31Z)
• Self-supervised Pre-training with Masked Shape Prediction for 3D Scene Understanding [106.0876425365599]
  Masked Shape Prediction (MSP) is a new framework to conduct masked signal modeling in 3D scenes. MSP uses the essential 3D semantic cue, i.e., geometric shape, as the prediction target for masked points.
  arXiv  Detail & Related papers  (2023-05-08T20:09:19Z)
• GMA3D: Local-Global Attention Learning to Estimate Occluded Motions of Scene Flow [3.2738068278607426]
  We propose a GMA3D module based on the transformer framework to infer the motion information of occluded points from the motion information of local and global non-occluded points respectively. Experiments show that our GMA3D can solve the occlusion problem in the scene flow, especially in the real scene.
  arXiv  Detail & Related papers  (2022-10-07T03:09:00Z)
• 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)
• Learning Scene Flow in 3D Point Clouds with Noisy Pseudo Labels [71.11151016581806]
  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.
  arXiv  Detail & Related papers  (2022-03-23T18:20:03Z)
• 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)
• Weakly Supervised Learning of Rigid 3D Scene Flow [81.37165332656612]
  We propose a data-driven scene flow estimation algorithm exploiting the observation that many 3D scenes can be explained by a collection of agents moving as rigid bodies. We showcase the effectiveness and generalization capacity of our method on four different autonomous driving datasets.
  arXiv  Detail & Related papers  (2021-02-17T18:58:02Z)
• Do not trust the neighbors! Adversarial Metric Learning for Self-Supervised Scene Flow Estimation [0.0]
  Scene flow is the task of estimating 3D motion vectors to individual points of a dynamic 3D scene. We propose a 3D scene flow benchmark and a novel self-supervised setup for training flow models. We find that our setup is able to keep motion coherence and preserve local geometries, which many self-supervised baselines fail to grasp.
  arXiv  Detail & Related papers  (2020-11-01T17:41:32Z)
• 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.