JunjH / Revisiting_single_depth_estimation
official implementation of "Revisiting Single Image Depth Estimation: Toward Higher Resolution Maps with Accurate Object Boundaries"
Stars: ✭ 271
Programming Languages
python
139335 projects - #7 most used programming language
Projects that are alternatives of or similar to Revisiting single depth estimation
arkit-virtual-backdrop
Superimposes your image into a 3D world using Metal+Arkit
Stars: ✭ 78 (-71.22%)
Mutual labels: depth
one-click-tangle
"One Click Tangle" intends to make lives easier to IOTA adopters by providing pre-configured scripts and recipes that allow to deploy IOTA Networks and Nodes "in one click".
Stars: ✭ 43 (-84.13%)
Mutual labels: depth
BlindAid
Capstone Project: Assist the blind in moving around safely by warning them of impending obstacles using depth sensing, computer vision, and tactile glove feedback.
Stars: ✭ 14 (-94.83%)
Mutual labels: depth
Structured-Light-Laser-Stripe-Reconstruction
Reconstructs a 3D stripe on the area of an object on which a laser falls as seen by the camera
Stars: ✭ 35 (-87.08%)
Mutual labels: depth
Crypto Exchange
Pulls together list of crypto exchanges to interact with their API's in a uniform fashion.
Stars: ✭ 241 (-11.07%)
Mutual labels: depth
learning-topology-synthetic-data
Tensorflow implementation of Learning Topology from Synthetic Data for Unsupervised Depth Completion (RAL 2021 & ICRA 2021)
Stars: ✭ 22 (-91.88%)
Mutual labels: depth
Three-Filters-to-Normal
Three-Filters-to-Normal: An Accurate and Ultrafast Surface Normal Estimator (RAL+ICRA'21)
Stars: ✭ 41 (-84.87%)
Mutual labels: depth
G2LTex
Code for CVPR 2018 paper --- Texture Mapping for 3D Reconstruction with RGB-D Sensor
Stars: ✭ 104 (-61.62%)
Mutual labels: depth
Depth-Guided-Inpainting
Code for ECCV 2020 "DVI: Depth Guided Video Inpainting for Autonomous Driving"
Stars: ✭ 50 (-81.55%)
Mutual labels: depth
Fall-Detection-Dataset
FUKinect-Fall dataset was created using Kinect V1. The dataset includes walking, bending, sitting, squatting, lying and falling actions performed by 21 subjects between 19-72 years of age.
Stars: ✭ 16 (-94.1%)
Mutual labels: depth
diskusage
FANTASTIC SPEED utility to find out top largest folders/files on the disk.
Stars: ✭ 64 (-76.38%)
Mutual labels: depth
MSG-Net
Depth Map Super-Resolution by Deep Multi-Scale Guidance, ECCV 2016
Stars: ✭ 76 (-71.96%)
Mutual labels: depth
M4Depth
Official implementation of the network presented in the paper "M4Depth: A motion-based approach for monocular depth estimation on video sequences"
Stars: ✭ 62 (-77.12%)
Mutual labels: depth
tx2 fcnn node
ROS node for real-time FCNN depth reconstruction
Stars: ✭ 102 (-62.36%)
Mutual labels: depth
plenopticam
Light-field imaging application for plenoptic cameras
Stars: ✭ 111 (-59.04%)
Mutual labels: depth
depth-from-defocus-and-correspondence
⛄Depth from Combining Defocus and Correspondence Using Light-Field Cameras.
Stars: ✭ 17 (-93.73%)
Mutual labels: depth
Revisiting Single Image Depth Estimation: Toward Higher Resolution Maps with Accurate Object Boundaries
Junjie Hu, Mete Ozay, Yan Zhang, Takayuki Okatani https://arxiv.org/abs/1803.08673
Results
Dependencies
- python 2.7
- Pytorch 0.3.1
Running
Download the trained models:
Depth estimation networks
Download the data:
NYU-v2 dataset
-
Demo
python demo.py
-
Test
python test.py
-
Train
python train.py
Citation
If you use the code or the pre-processed data, please cite:
@inproceedings{Hu2019RevisitingSI,
title={Revisiting Single Image Depth Estimation: Toward Higher Resolution Maps With Accurate Object Boundaries},
author={Junjie Hu and Mete Ozay and Yan Zhang and Takayuki Okatani},
journal={2019 IEEE Winter Conference on Applications of Computer Vision (WACV)},
year={2019}
}
Note that the project description data, including the texts, logos, images, and/or trademarks,
for each open source project belongs to its rightful owner.
If you wish to add or remove any projects, please contact us at [email protected].