Scalable Scene Flow from Point Clouds in the Real World

• URL: http://arxiv.org/abs/2103.01306v2
• Date: Wed, 3 Mar 2021 20:06:15 GMT
• Title: Scalable Scene Flow from Point Clouds in the Real World
• Authors: Philipp Jund, Chris Sweeney, Nichola Abdo, Zhifeng Chen, Jonathon Shlens
• Abstract summary: We introduce a new large scale benchmark for scene flow based on the Open dataset. We show how previous works were bounded based on the amount of real LiDAR data available. We introduce the model architecture FastFlow3D that provides real time inference on the full point cloud.
• Score: 30.437100097997245
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Autonomous vehicles operate in highly dynamic environments necessitating an accurate assessment of which aspects of a scene are moving and where they are moving to. A popular approach to 3D motion estimation -- termed scene flow -- is to employ 3D point cloud data from consecutive LiDAR scans, although such approaches have been limited by the small size of real-world, annotated LiDAR data. In this work, we introduce a new large scale benchmark for scene flow based on the Waymo Open Dataset. The dataset is $\sim$1,000$\times$ larger than previous real-world datasets in terms of the number of annotated frames and is derived from the corresponding tracked 3D objects. We demonstrate how previous works were bounded based on the amount of real LiDAR data available, suggesting that larger datasets are required to achieve state-of-the-art predictive performance. Furthermore, we show how previous heuristics for operating on point clouds such as artificial down-sampling heavily degrade performance, motivating a new class of models that are tractable on the full point cloud. To address this issue, we introduce the model architecture FastFlow3D that provides real time inference on the full point cloud. Finally, we demonstrate that this problem is amenable to techniques from semi-supervised learning by highlighting open problems for generalizing methods for predicting motion on unlabeled objects. We hope that this dataset may provide new opportunities for developing real world scene flow systems and motivate a new class of machine learning problems.

Related papers

• MonST3R: A Simple Approach for Estimating Geometry in the Presence of Motion [118.74385965694694]
  We present Motion DUSt3R (MonST3R), a novel geometry-first approach that directly estimates per-timestep geometry from dynamic scenes. By simply estimating a pointmap for each timestep, we can effectively adapt DUST3R's representation, previously only used for static scenes, to dynamic scenes. We show that by posing the problem as a fine-tuning task, identifying several suitable datasets, and strategically training the model on this limited data, we can surprisingly enable the model to handle dynamics.
  arXiv  Detail & Related papers  (2024-10-04T18:00:07Z)
• OPUS: Occupancy Prediction Using a Sparse Set [64.60854562502523]
  We present a framework to simultaneously predict occupied locations and classes using a set of learnable queries. OPUS incorporates a suite of non-trivial strategies to enhance model performance. Our lightest model achieves superior RayIoU on the Occ3D-nuScenes dataset at near 2x FPS, while our heaviest model surpasses previous best results by 6.1 RayIoU.
  arXiv  Detail & Related papers  (2024-09-14T07:44:22Z)
• 3DSFLabelling: Boosting 3D Scene Flow Estimation by Pseudo Auto-labelling [21.726386822643995]
  We present a novel approach to generate a large number of 3D scene flow pseudo labels for real-world LiDAR point clouds. Specifically, we employ the assumption of rigid body motion to simulate potential object-level rigid movements in autonomous driving scenarios. By perfectly synthesizing target point clouds based on augmented motion parameters, we easily obtain lots of 3D scene flow labels in point clouds highly consistent with real scenarios.
  arXiv  Detail & Related papers  (2024-02-28T08:12:31Z)
• Contrastive Lift: 3D Object Instance Segmentation by Slow-Fast Contrastive Fusion [110.84357383258818]
  We propose a novel approach to lift 2D segments to 3D and fuse them by means of a neural field representation. The core of our approach is a slow-fast clustering objective function, which is scalable and well-suited for scenes with a large number of objects. Our approach outperforms the state-of-the-art on challenging scenes from the ScanNet, Hypersim, and Replica datasets.
  arXiv  Detail & Related papers  (2023-06-07T17:57:45Z)
• WOMD-LiDAR: Raw Sensor Dataset Benchmark for Motion Forecasting [38.95768804529958]
  We augment the Open Motion dataset with large-scale, high-quality, diverse LiDAR data for the motion forecasting task. The new augmented dataset WOMD-LiDAR consists of over 100,000 scenes that each spans 20 seconds, consisting of well-synchronized and high quality LiDAR point clouds captured across a range of urban and suburban geographies. Experiments show that the LiDAR data brings improvement in the motion forecasting task.
  arXiv  Detail & Related papers  (2023-04-07T20:23:15Z)
• Instance-incremental Scene Graph Generation from Real-world Point Clouds via Normalizing Flows [9.4858987199432]
  This work introduces a new task of instance-incremental scene graph generation: Given a scene of the point cloud, representing it as a graph and automatically increasing novel instances. A graph denoting the object layout of the scene is finally generated. It helps to guide the insertion of novel 3D objects into a real-world scene in vision-based applications like augmented reality.
  arXiv  Detail & Related papers  (2023-02-21T03:34:15Z)
• Point-Syn2Real: Semi-Supervised Synthetic-to-Real Cross-Domain Learning for Object Classification in 3D Point Clouds [14.056949618464394]
  Object classification using LiDAR 3D point cloud data is critical for modern applications such as autonomous driving. We propose a semi-supervised cross-domain learning approach that does not rely on manual annotations of point clouds. We introduce Point-Syn2Real, a new benchmark dataset for cross-domain learning on point clouds.
  arXiv  Detail & Related papers  (2022-10-31T01:53:51Z)
• Learning Scene Dynamics from Point Cloud Sequences [8.163697683448811]
  We propose a novel problem --temporal scene flow estimation (SSFE) -- that aims to predict 3D scene flow for all pairs of point clouds in a sequence. We introduce the SPCM-Net architecture, which solves this problem by computing multi-scale correlations between neighboring point clouds. We demonstrate that this approach can be effectively modified for sequential point cloud forecasting.
  arXiv  Detail & Related papers  (2021-11-16T19:52:46Z)
• Lifting 2D Object Locations to 3D by Discounting LiDAR Outliers across Objects and Views [70.1586005070678]
  We present a system for automatically converting 2D mask object predictions and raw LiDAR point clouds into full 3D bounding boxes of objects. Our method significantly outperforms previous work despite the fact that those methods use significantly more complex pipelines, 3D models and additional human-annotated external sources of prior information.
  arXiv  Detail & Related papers  (2021-09-16T13:01:13Z)
• RandomRooms: Unsupervised Pre-training from Synthetic Shapes and Randomized Layouts for 3D Object Detection [138.2892824662943]
  A promising solution is to make better use of the synthetic dataset, which consists of CAD object models, to boost the learning on real datasets. Recent work on 3D pre-training exhibits failure when transfer features learned on synthetic objects to other real-world applications. In this work, we put forward a new method called RandomRooms to accomplish this objective.
  arXiv  Detail & Related papers  (2021-08-17T17:56:12Z)
• 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)

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.