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

PyTorch Implementation of our paper Explain Me the Painting: Multi-Topic Knowledgeable Art Description Generation

modelvshuman is a Python library to benchmark the gap between human and machine vision

A simplistic and efficient pure-python neural network library from Phys Whiz with CPU and GPU support.

LTR_CrossEncoder: Legal Text Retrieval Zalo AI Challenge 2021

Flower - A Friendly Federated Learning Framework

A check for whether the dependency jobs are all green.

A general python framework for single object tracking in LiDAR point clouds, based on PyTorch Lightning.

The official repository for our paper "The Devil is in the Detail: Simple Tricks Improve Systematic Generalization of Transformers". We significantly improve the systematic generalization of transformer models on a variety of datasets using simple tricks and careful considerations.

So-ViT: Mind Visual Tokens for Vision Transformer

A comprehensive and up-to-date developer education platform for Urbit.

Multi-Modal Machine Learning toolkit based on PyTorch.

Multi-Task Learning as a Bargaining Game

Efficient 6-DoF Grasp Generation in Cluttered Scenes

An investigation project for SISR.

Implementation of U-Net and SegNet for building segmentation

Code and real data for the paper "Counterfactual Temporal Point Processes", available at arXiv.

An example of time series augmentation methods with Keras

This is the code for CVPR 2021 oral paper: Jigsaw Clustering for Unsupervised Visual Representation Learning

Codes for 'Dual Parameterization of Sparse Variational Gaussian Processes'

MoCoPnet - Deformable 3D Convolution for Video Super-Resolution