Neural Scene Flow Prior (NeurIPS 2021 spotlight)

Last update: Jan 03, 2023

Overview

Neural Scene Flow Prior

Xueqian Li, Jhony Kaesemodel Pontes, Simon Lucey

Will appear on Thirty-fifth Conference on Neural Information Processing Systems (NeurIPS, 2021) as spotlight.

arXiv link: https://arxiv.org/pdf/2111.01253.pdf

Scene flow results on Argoverse
Point cloud integration (left: densified point cloud; right: sparse point cloud)

Prerequisites

This code is based on PyTorch implementation, and tested on torch=1.6.0 with CUDA 10.1 OR torch=1.7.1 with CUDA 10.2.

For a detailed installation guide, please go to requirements.txt.

Dataset

We provide four datasets we used in our paper. You may download datasets used in the paper from these anonymous links:

KITTI (266MB)
Argoverse (5.3GB)
nuScenes (436MB)
FlyingThings3D (436MB)

After you download the dataset, you can create a symbolic link in the ./dataset folder as ./dataset/kitti, ./dataset/argoverse, ./dataset/nuscenes, and ./dataset/flyingthings.

Optimization

Since we use neural scene flow prior for runtime optimization, our method does not include any "training".

Just run following lines for a simple optimization on a small KITTI Scene Flow dataset (only 50 testing samples)

python optimization.py \
--dataset KITTISceneFlowDataset \
--dataset_path dataset/kitti \
--exp_name KITTI_2048_points \
--batch_size 1 \
--iters 5000 \
--compute_metrics \
--num_points 2048 \
--hidden_units 128 \
--lr 0.008 \
--backward_flow \
--early_patience 70 \
--visualize

You can then play with these configurations. We provide commands we used to generate results in the small point coud (2048 points) experiments and large point cloud (all points included) experiments.

1. small point cloud (2048 points)

KITTI Scene Flow

python optimization.py \
--dataset KITTISceneFlowDataset \
--dataset_path dataset/kitti \
--exp_name KITTI_2048_points \
--batch_size 1 \
--iters 5000 \
--compute_metrics \
--num_points 2048 \
--hidden_units 128 \
--lr 0.008 \
--backward_flow \
--early_patience 70 \
--visualize

Argoverse Scene Flow

python optimization.py \
--dataset ArgoverseSceneFlowDataset \
--dataset_path dataset/argoverse \
--exp_name Argoverse_2048_points \
--batch_size 1 \
--iters 5000 \
--compute_metrics \
--num_points 2048 \
--hidden_units 128 \
--lr 0.008 \
--backward_flow \
--early_patience 30 \
--visualize

nuScenes Scene Flow

python optimization.py \
--dataset NuScenesSceneFlowDataset \
--dataset_path dataset/nuscenes \
--exp_name Argoverse_2048_points \
--batch_size 1 \
--iters 5000 \
--compute_metrics \
--num_points 2048 \
--hidden_units 128 \
--lr 0.008 \
--backward_flow \
--early_patience 30 \
--visualize

FlyingThings3D

python optimization.py \
--dataset FlyingThings3D \
--dataset_path dataset/flyingthings \
--exp_name FlyingThings_2048_points \
--batch_size 1 \
--iters 5000 \
--compute_metrics \
--num_points 2048 \
--hidden_units 128 \
--lr 0.008 \
--backward_flow \
--early_patience 30 \
--visualize

2. dense point cloud (all points included)

KITTI Scene Flow

python optimization.py \
--dataset KITTISceneFlowDataset \
--dataset_path dataset/kitti \
--exp_name KITTI_2048_points \
--batch_size 1 \
--iters 5000 \
--compute_metrics \
--use_all_points \
--hidden_units 128 \
--lr 0.001 \
--early_patience 100 \
--visualize

Argoverse Scene Flow

python optimization.py \
--dataset ArgoverseSceneFlowDataset \
--dataset_path dataset/argoverse \
--exp_name Argoverse_2048_points \
--batch_size 1 \
--iters 5000 \
--compute_metrics \
--use_all_points \
--hidden_units 128 \
--lr 0.003 \
--backward_flow \
--early_patience 100 \
--visualize

Contributing

If you find the project useful for your research, you may cite,

@article{li2021neural,
  title={Neural scene flow prior},
  author={Li, Xueqian and Pontes, Jhony Kaesemodel and Lucey, Simon},
  journal={arXiv preprint arXiv:2111.01253},
  year={2021}
}

Neural Scene Flow Prior (NeurIPS 2021 spotlight)

Related tags

Overview

Neural Scene Flow Prior

Scene flow results on Argoverse

Point cloud integration (left: densified point cloud; right: sparse point cloud)

Prerequisites

Dataset

Optimization

1. small point cloud (2048 points)

KITTI Scene Flow

Argoverse Scene Flow

nuScenes Scene Flow

FlyingThings3D

2. dense point cloud (all points included)

KITTI Scene Flow

Argoverse Scene Flow

Contributing

Owner

Lilac Lee

Dataset and codebase for NeurIPS 2021 paper: Exploring Forensic Dental Identification with Deep Learning

A U-Net combined with a variational auto-encoder that is able to learn conditional distributions over semantic segmentations.

Opinionated code formatter, just like Python's black code formatter but for Beancount

Prototypical Cross-Attention Networks for Multiple Object Tracking and Segmentation, NeurIPS 2021 Spotlight

(to be released) [NeurIPS'21] Transformers Generalize DeepSets and Can be Extended to Graphs and Hypergraphs

FastReID is a research platform that implements state-of-the-art re-identification algorithms.

Official PyTorch Implementation of Embedding Transfer with Label Relaxation for Improved Metric Learning, CVPR 2021

RLMeta is a light-weight flexible framework for Distributed Reinforcement Learning Research.

MinkLoc3D-SI: 3D LiDAR place recognition with sparse convolutions,spherical coordinates, and intensity

Code for "Diffusion is All You Need for Learning on Surfaces"

LightningFSL: Pytorch-Lightning implementations of Few-Shot Learning models.

BASH - Biomechanical Animated Skinned Human

The code for "Deep Level Set for Box-supervised Instance Segmentation in Aerial Images".

Implementation of Shape and Electrostatic similarity metric in deepFMPO.

Learning with Subset Stacking

A novel pipeline framework for multi-hop complex KGQA task. About the paper title: Improving Multi-hop Embedded Knowledge Graph Question Answering by Introducing Relational Chain Reasoning

This library is a location of the LegacyLogger for PyTorch Lightning.

A MatConvNet-based implementation of the Fully-Convolutional Networks for image segmentation

code for ICCV 2021 paper 'Generalized Source-free Domain Adaptation'