Office source code of paper UniFuse: Unidirectional Fusion for 360$^\circ$ Panorama Depth Estimation

Last update: Dec 26, 2022

Overview

UniFuse (RAL+ICRA2021)

Office source code of paper UniFuse: Unidirectional Fusion for 360$^\circ$ Panorama Depth Estimation, arXiv, Demo

Preparation

Installation

Environments

python 3.6
Pytorch >= 1.0.0
CUDA >= 9.0

Install requirements

pip install -r requirements.txt

Datasets

Please download the preferred datasets, i.e., Matterport3D, Stanford2D3D, 3D60 and PanoSUNCG. For Matterport3D, please preprocess it following M3D-README.md.

Training

UniFuse on Matterport3D

python train.py --data_path $DATA_PATH \
-dataset matterport3d \
--model_name Matterport3D_UniFuse \
--batch_size 6 \
--num_epochs 100 \
--height 512 \
--width 1024 \
--imagenet_pretrained \
--net UniFuse

Equirectangular baseline on Matterport3D

python train.py --data_path $DATA_PATH \
-dataset matterport3d \
--model_name Matterport3D_Equi \
--batch_size 6 \
--num_epochs 100 \
--height 512 \
--width 1024 \
--imagenet_pretrained \
--net Equi

It is similar for other datasets.

Evaluation

Pre-trained models

The pre-trained models of UniFuse for 4 datasets are available, Matterport3D, Stanford2D3D, 3D60 and PanoSUNCG.

Test on a pre-trained model

python evaluate.py  --data_path $DATA_PATH --dataset matterport3d --load_weights_folder $MODEL_PATH

Citation

Please cite our paper if you find our work useful in your research.

@article{jiang2021unifuse,
      title={UniFuse: Unidirectional Fusion for 360$^{\circ}$ Panorama Depth Estimation}, 
      author={Hualie Jiang and Zhe Sheng and Siyu Zhu and Zilong Dong and Rui Huang},
	  journal={IEEE Robotics and Automation Letters},
	  year={2021},
	  publisher={IEEE}
}

Office source code of paper UniFuse: Unidirectional Fusion for 360$^\circ$ Panorama Depth Estimation

Related tags

Overview

UniFuse (RAL+ICRA2021)

Preparation

Installation

Datasets

Training

UniFuse on Matterport3D

Equirectangular baseline on Matterport3D

Evaluation

Pre-trained models

Test on a pre-trained model

Citation

Owner

Alibaba

Universal Probability Distributions with Optimal Transport and Convex Optimization

This repo includes the supplementary of our paper "CEMENT: Incomplete Multi-View Weak-Label Learning with Long-Tailed Labels"

Notebooks, slides and dataset of the CorrelAid Machine Learning Winter School

The Malware Open-source Threat Intelligence Family dataset contains 3,095 disarmed PE malware samples from 454 families

Causal Influence Detection for Improving Efficiency in Reinforcement Learning

Final project for machine learning (CSC 590). Detection of hepatitis C and progression through blood samples.

An efficient PyTorch library for Global Wheat Detection using YOLOv5. The project is based on this Kaggle competition Global Wheat Detection (2021).

Effect of Different Encodings and Distance Functions on Quantum Instance-based Classifiers

Predict the latency time of the deep learning models

Code for the paper "SmoothMix: Training Confidence-calibrated Smoothed Classifiers for Certified Robustness" (NeurIPS 2021)

StyleGAN2-ADA - Official PyTorch implementation

Collection of TensorFlow2 implementations of Generative Adversarial Network varieties presented in research papers.

This toolkit provides codes to download and pre-process the SLUE datasets, train the baseline models, and evaluate SLUE tasks.

This repo contains code to reproduce all experiments in Equivariant Neural Rendering

A PyTorch implementation of the Relational Graph Convolutional Network (RGCN).

Caffe: a fast open framework for deep learning.

This respository includes implementations on Manifoldron: Direct Space Partition via Manifold Discovery

Mixed Transformer UNet for Medical Image Segmentation

The 3rd place solution for competition

Display, filter and search log messages in your terminal