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 → uber-research → Deeppruner

uber-research / Deeppruner

Licence: other
DeepPruner: Learning Efficient Stereo Matching via Differentiable PatchMatch (ICCV 2019)

Programming Languages

python
139335 projects - #7 most used programming language

Labels

pytorchreal-time

Projects that are alternatives of or similar to Deeppruner

Chatify Demo
Chatify Laravel Package Demo application
Stars: ✭ 189 (-16.37%)
Mutual labels:  real-time
Pytorch realtime multi Person pose estimation
Pytorch version of Realtime Multi-Person Pose Estimation project
Stars: ✭ 205 (-9.29%)
Mutual labels:  real-time
Fast portrait segmentation
Fast (aimed to "real time") Portrait Segmentation on mobile phone
Stars: ✭ 215 (-4.87%)
Mutual labels:  real-time
Voronoi image manipulation
A system independent tool for interactive image manipulation with Voronoi and Delaunay data structures.
Stars: ✭ 196 (-13.27%)
Mutual labels:  real-time
Heart Rate Measurement Using Camera
real time application to measure heart rate
Stars: ✭ 202 (-10.62%)
Mutual labels:  real-time
Swellrt
SwellRT main project. Server, JavaScript and Java clients
Stars: ✭ 205 (-9.29%)
Mutual labels:  real-time
Opentok Ios Sdk Samples
Example applications that use the OpenTok iOS SDK
Stars: ✭ 186 (-17.7%)
Mutual labels:  real-time
Caffe2 Ios
Caffe2 on iOS Real-time Demo. Test with Your Own Model and Photos.
Stars: ✭ 221 (-2.21%)
Mutual labels:  real-time
Btrack
A Real-Time Beat Tracker
Stars: ✭ 204 (-9.73%)
Mutual labels:  real-time
Yave
Yet Another Vulkan Engine
Stars: ✭ 211 (-6.64%)
Mutual labels:  real-time
Mocapnet
We present MocapNET2, a real-time method that estimates the 3D human pose directly in the popular Bio Vision Hierarchy (BVH) format, given estimations of the 2D body joints originating from monocular color images. Our contributions include: (a) A novel and compact 2D pose NSRM representation. (b) A human body orientation classifier and an ensemble of orientation-tuned neural networks that regress the 3D human pose by also allowing for the decomposition of the body to an upper and lower kinematic hierarchy. This permits the recovery of the human pose even in the case of significant occlusions. (c) An efficient Inverse Kinematics solver that refines the neural-network-based solution providing 3D human pose estimations that are consistent with the limb sizes of a target person (if known). All the above yield a 33% accuracy improvement on the Human 3.6 Million (H3.6M) dataset compared to the baseline method (MocapNET) while maintaining real-time performance (70 fps in CPU-only execution).
Stars: ✭ 194 (-14.16%)
Mutual labels:  real-time
Thunderpush
Push messages to browsers in real-time ⚡️
Stars: ✭ 202 (-10.62%)
Mutual labels:  real-time
Laravel Echo Server
Socket.io server for Laravel Echo
Stars: ✭ 2,487 (+1000.44%)
Mutual labels:  real-time
A2j
Code for paper "A2J: Anchor-to-Joint Regression Network for 3D Articulated Pose Estimation from a Single Depth Image". ICCV2019
Stars: ✭ 190 (-15.93%)
Mutual labels:  real-time
Sanity
The Sanity Studio – Collaborate in real-time on structured content
Stars: ✭ 3,007 (+1230.53%)
Mutual labels:  real-time
Centerface.pytorch
unofficial version of centerface, which achieves the best balance between speed and accuracy at face detection
Stars: ✭ 187 (-17.26%)
Mutual labels:  real-time
Feathers
A framework for real-time applications and REST APIs with JavaScript and TypeScript
Stars: ✭ 13,761 (+5988.94%)
Mutual labels:  real-time
Omniscidb
OmniSciDB (formerly MapD Core)
Stars: ✭ 2,601 (+1050.88%)
Mutual labels:  real-time
Fairmot
[IJCV-2021] FairMOT: On the Fairness of Detection and Re-Identification in Multi-Object Tracking
Stars: ✭ 3,194 (+1313.27%)
Mutual labels:  real-time
Rtm3d
Unofficial PyTorch implementation of "RTM3D: Real-time Monocular 3D Detection from Object Keypoints for Autonomous Driving" (ECCV 2020)
Stars: ✭ 211 (-6.64%)
Mutual labels:  real-time
View All Similar Projects ➔

DeepPruner: Learning Efficient Stereo Matching via Differentiable PatchMatch

This repository releases code for our paper DeepPruner: Learning Efficient Stereo Matching via Differentiable PatchMatch.

Table of Contents

DeepPruner
Differentiable Patch Match
Requirements (Major Dependencies)
Citation

DeepPruner

  • An efficient "Real Time Stereo Matching" algorithm, which takes as input 2 images and outputs a disparity (or depth) map.

  • Results/ Metrics:

    • KITTI: Results competitive to SOTA, while being real-time (8x faster than SOTA). SOTA among published real-time algorithms.

    • ETH3D: SOTA among all ROB entries.

    • SceneFlow: 2nd among all published algorithms, while being 8x faster than the 1st.

    • Runtime: 62ms (for DeepPruner-fast), 180ms (for DeepPruner-best)

    • Cuda Memory Requirements: 805MB (for DeepPruner-best)

Differentiable Patch Match

  • Fast algorithm for finding dense nearest neighbor correspondences between patches of images regions. Differentiable version of the generalized Patch Match algorithm. (Barnes et al.)

More details in the corresponding folder README.

Requirements (Major Dependencies)

  • Pytorch (0.4.1+)
  • Python2.7
  • torchvision (0.2.0+)

Citation

If you use our source code, or our paper, please consider citing the following:

@inproceedings{Duggal2019ICCV,
title = {DeepPruner: Learning Efficient Stereo Matching via Differentiable PatchMatch},
author = {Shivam Duggal and Shenlong Wang and Wei-Chiu Ma and Rui Hu and Raquel Urtasun},
booktitle = {ICCV},
year = {2019} }

Correspondences to Shivam Duggal s[email protected], Shenlong Wang [email protected], Wei-Chiu Ma [email protected]

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].