Open AccessPosted Content
HPLFlowNet: Hierarchical Permutohedral Lattice FlowNet for Scene Flow Estimation on Large-scale Point Clouds
TL;DR: In this paper, the authors propose novel DownBCLayers, UpBCL, and CorrBCL operations that restore structural information from unstructured point clouds, and fuse information from two consecutive point clouds.
read more
Abstract: We present a novel deep neural network architecture for end-to-end scene flow estimation that directly operates on large-scale 3D point clouds. Inspired by Bilateral Convolutional Layers (BCL), we propose novel DownBCL, UpBCL, and CorrBCL operations that restore structural information from unstructured point clouds, and fuse information from two consecutive point clouds. Operating on discrete and sparse permutohedral lattice points, our architectural design is parsimonious in computational cost. Our model can efficiently process a pair of point cloud frames at once with a maximum of 86K points per frame. Our approach achieves state-of-the-art performance on the FlyingThings3D and KITTI Scene Flow 2015 datasets. Moreover, trained on synthetic data, our approach shows great generalization ability on real-world data and on different point densities without fine-tuning.
read more
Chat with Paper
AI Agents for this Paper
Find similar papers on Google Scholar, PubMed and Arxiv
Write a critical review of this paper
Analyze citations of this paper to find unaddressed research gaps
Citations
Deep Learning for 3D Point Clouds: A Survey
TL;DR: This paper presents a comprehensive review of recent progress in deep learning methods for point clouds, covering three major tasks, including 3D shape classification, 3D object detection and tracking, and 3D point cloud segmentation.
PointPWC-Net: Cost Volume on Point Clouds for (Self-)Supervised Scene Flow Estimation
Wenxuan Wu,Zhi Yuan Wang,Zhuwen Li,Wei Liu,Li Fuxin +4 more
- 23 Aug 2020
TL;DR: A novel end-to-end deep scene flow model, called PointPWC-Net, that directly processes 3D point cloud scenes with large motions in a coarse- to-fine fashion, and shows great generalization ability on the KITTI Scene Flow 2015 dataset, outperforming all previous methods.
239
Just Go With the Flow: Self-Supervised Scene Flow Estimation
Himangi Mittal,Brian Okorn,David Held +2 more
- 14 Jun 2020
TL;DR: This work presents a method of training scene flow that uses two self-supervised losses, based on nearest neighbors and cycle consistency, which matches current state-of-the-art supervised performance using no real world annotations and exceeds state- of- the-art performance when combining the self- supervised approach with supervised learning on a smaller labeled dataset.
FLOT: Scene Flow on Point Clouds Guided by Optimal Transport.
Gilles Puy,Alexandre Boulch,Renaud Marlet +2 more
- 23 Aug 2020
TL;DR: In this article, the authors propose a method called FLOT that estimates scene flow on point clouds based on the pairwise similarity between deep features extracted by a neural network trained under full supervision using synthetic datasets.
137
•Posted Content
Offboard 3D Object Detection from Point Cloud Sequences
TL;DR: This paper designs the offboard detector to make use of the temporal points through both multi-frame object detection and novel objectcentric refinement models, and proposes a novel offboard 3D object detection pipeline using point cloud sequence data.
130
References
•Proceedings Article
Adam: A Method for Stochastic Optimization
Diederik P. Kingma,Jimmy Ba +1 more
- 01 Jan 2015
TL;DR: This work introduces Adam, an algorithm for first-order gradient-based optimization of stochastic objective functions, based on adaptive estimates of lower-order moments, and provides a regret bound on the convergence rate that is comparable to the best known results under the online convex optimization framework.
138.5K
U-Net: Convolutional Networks for Biomedical Image Segmentation
Olaf Ronneberger,Philipp Fischer,Thomas Brox +2 more
- 05 Oct 2015
TL;DR: Neber et al. as discussed by the authors proposed a network and training strategy that relies on the strong use of data augmentation to use the available annotated samples more efficiently, which can be trained end-to-end from very few images and outperforms the prior best method (a sliding-window convolutional network) on the ISBI challenge for segmentation of neuronal structures in electron microscopic stacks.
Fully convolutional networks for semantic segmentation
Jonathan Long,Evan Shelhamer,Trevor Darrell +2 more
- 07 Jun 2015
TL;DR: The key insight is to build “fully convolutional” networks that take input of arbitrary size and produce correspondingly-sized output with efficient inference and learning.
A method for registration of 3-D shapes
Paul J. Besl,H.D. McKay +1 more
TL;DR: In this paper, the authors describe a general-purpose representation-independent method for the accurate and computationally efficient registration of 3D shapes including free-form curves and surfaces, based on the iterative closest point (ICP) algorithm, which requires only a procedure to find the closest point on a geometric entity to a given point.
20.6K
•Posted Content
U-Net: Convolutional Networks for Biomedical Image Segmentation
TL;DR: It is shown that such a network can be trained end-to-end from very few images and outperforms the prior best method (a sliding-window convolutional network) on the ISBI challenge for segmentation of neuronal structures in electron microscopic stacks.
19.5K