GitPlanet

Cheap and reliable Node.js hosting starts at $3/month, and $1/month static HTML hosting

Created with love in Canada, visit hostnodejs.com today

Feel like to post an Ad? Learn Details
All Projects → dontLoveBugs → CSPN_monodepth

dontLoveBugs / CSPN_monodepth

Licence: other
Unofficial Faster PyTorch implementation of Convolutional Spatial Propagation Network

Programming Languages

python
139335 projects - #7 most used programming language
Cuda
1817 projects
C++
36643 projects - #6 most used programming language
c
50402 projects - #5 most used programming language
shell
77523 projects

Labels

pytorchdepth-completionmonocular-depth-estimationcspn

Projects that are alternatives of or similar to CSPN monodepth

DiverseDepth
The code and data of DiverseDepth
Stars: ✭ 150 (+127.27%)
Mutual labels:  monocular-depth-estimation
ForeSeE
Task-Aware Monocular Depth Estimation for 3D Object Detection, AAAI2020
Stars: ✭ 58 (-12.12%)
Mutual labels:  monocular-depth-estimation
Visualizing-CNNs-for-monocular-depth-estimation
official implementation of "Visualization of Convolutional Neural Networks for Monocular Depth Estimation"
Stars: ✭ 120 (+81.82%)
Mutual labels:  monocular-depth-estimation
MonoDEVSNet
Official PyTorch implementation of MonoDEVSNet - "Monocular Depth Estimation through Virtual-world Supervision and Real-world SfM Self-Supervision."
Stars: ✭ 34 (-48.48%)
Mutual labels:  monocular-depth-estimation
temporal-depth-segmentation
Source code (train/test) accompanying the paper entitled "Veritatem Dies Aperit - Temporally Consistent Depth Prediction Enabled by a Multi-Task Geometric and Semantic Scene Understanding Approach" in CVPR 2019 (https://arxiv.org/abs/1903.10764).
Stars: ✭ 20 (-69.7%)
Mutual labels:  monocular-depth-estimation
SGDepth
[ECCV 2020] Self-Supervised Monocular Depth Estimation: Solving the Dynamic Object Problem by Semantic Guidance
Stars: ✭ 162 (+145.45%)
Mutual labels:  monocular-depth-estimation
EPCDepth
[ICCV 2021] Excavating the Potential Capacity of Self-Supervised Monocular Depth Estimation
Stars: ✭ 105 (+59.09%)
Mutual labels:  monocular-depth-estimation
void-dataset
Visual Odometry with Inertial and Depth (VOID) dataset
Stars: ✭ 74 (+12.12%)
Mutual labels:  depth-completion
Reversing
Code for "Reversing the cycle: self-supervised deep stereo through enhanced monocular distillation"
Stars: ✭ 43 (-34.85%)
Mutual labels:  monocular-depth-estimation
PENet ICRA2021
ICRA 2021 "Towards Precise and Efficient Image Guided Depth Completion"
Stars: ✭ 256 (+287.88%)
Mutual labels:  depth-completion
learning-topology-synthetic-data
Tensorflow implementation of Learning Topology from Synthetic Data for Unsupervised Depth Completion (RAL 2021 & ICRA 2021)
Stars: ✭ 22 (-66.67%)
Mutual labels:  depth-completion
rectified-features
[ECCV 2020] Single image depth prediction allows us to rectify planar surfaces in images and extract view-invariant local features for better feature matching
Stars: ✭ 57 (-13.64%)
Mutual labels:  monocular-depth-estimation
Depth estimation
Deep learning model to estimate the depth of image.
Stars: ✭ 62 (-6.06%)
Mutual labels:  monocular-depth-estimation
FisheyeDistanceNet
FisheyeDistanceNet
Stars: ✭ 33 (-50%)
Mutual labels:  monocular-depth-estimation

CSPN implemented in Pytorch 0.4.1

Introduction

This is a PyTorch(0.4.1) implementation of Depth Estimation via Affinity Learned with Convolutional Spatial Propagation Network. At present, we can provide train script in NYU Depth V2 dataset for depth completion and monocular depth estimation. KITTI will be available soon!

Faster Implementation

We re-implement CSPN using Pixel-Adaptive Convolution.

Multi_GPU

The implementation of multi-gpus is based on inplace abn.

Results

Method Implementation details rml rmse log10 Delta1 Delta2 Delta3
Paper batch size=24 epoch=40 0.016 0.117 - 0.992 0.999 1.000
Our_impl batch size=8 iteration=100k 0.018 0.127 0.008 0.991 0.998 1.000
Our_CSPN batch size=8 iteration=100k 0.018 0.127 0.008 0.991 0.998 1.000

Image text

Third Libs

inplace abn

Pixel-Adaptive Convolution

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].