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

ML powered analytics engine for outlier detection and root cause analysis.

FCAF3D: Fully Convolutional Anchor-Free 3D Object Detection

This is official implementaion of paper "Token Shift Transformer for Video Classification".

Demonstrates how to divide a DL model into multiple IR model files (division) and introduce a simplest way to implement a custom layer works with OpenVINO IR models.

PyTorch implementation of our paper How robust are discriminatively trained zero-shot learning models?

A simple, fully convolutional model for real-time instance segmentation.

A Semantic Segmentation Network for Urban-Scale Building Footprint Extraction Using RGB Satellite Imagery

Large-scale Hyperspectral Image Clustering Using Contrastive Learning, CIKM 21 Workshop

DiSECt: Differentiable Simulator for Robotic Cutting

🌾 PASTIS 🌾 Panoptic Agricultural Satellite TIme Series

Fuse radar and camera for detection

TensorFlowOnSpark brings TensorFlow programs to Apache Spark clusters.

Code for "FGR: Frustum-Aware Geometric Reasoning for Weakly Supervised 3D Vehicle Detection", ICRA 2021

Learnable Motion Coherence for Correspondence Pruning

Open Source Light Field Toolbox for Super-Resolution

[NIPS 2021] UOTA: Improving Self-supervised Learning with Automated Unsupervised Outlier Arbitration.

A PyTorch implementation of the continual learning experiments with deep neural networks

SegTransVAE: Hybrid CNN - Transformer with Regularization for medical image segmentation

Evaluating Privacy-Preserving Machine Learning in Critical Infrastructures: A Case Study on Time-Series Classification

A framework for attentive explainable deep learning on tabular data