All Projects → JiaRenChang → RealtimeStereo

JiaRenChang / RealtimeStereo

Licence: GPL-3.0 license
Attention-Aware Feature Aggregation for Real-time Stereo Matching on Edge Devices (ACCV, 2020)

Programming Languages

python
139335 projects - #7 most used programming language
shell
77523 projects

Projects that are alternatives of or similar to RealtimeStereo

SASensorProcessing
ROS node to create pointcloud out of stereo images from the KITTI Vision Benchmark Suite
Stars: ✭ 26 (-76.36%)
Mutual labels:  stereo-vision, stereo-matching
semi-global-matching
Semi-Global Matching
Stars: ✭ 122 (+10.91%)
Mutual labels:  stereo-vision, stereo-matching
Pandora
A stereo matching framework that will help you design your stereo matching pipeline with state of the art performances.
Stars: ✭ 31 (-71.82%)
Mutual labels:  stereo-vision, stereo-matching
ONNX-HITNET-Stereo-Depth-estimation
Python scripts form performing stereo depth estimation using the HITNET model in ONNX.
Stars: ✭ 21 (-80.91%)
Mutual labels:  stereo-vision, stereo-matching
Openmvs
open Multi-View Stereo reconstruction library
Stars: ✭ 1,842 (+1574.55%)
Mutual labels:  stereo-vision, stereo-matching
UAV-Stereo-Vision
A program for controlling a micro-UAV for obstacle detection and collision avoidance using disparity mapping
Stars: ✭ 30 (-72.73%)
Mutual labels:  stereo-vision, stereo-matching
edlsm pytorch
Pytorch implementation for stereo matching described in the paper: Efficient Deep learning for stereo matching
Stars: ✭ 16 (-85.45%)
Mutual labels:  stereo-vision, stereo-matching
PatchMatchCuda
The PatchMatch stereo match algorithm implemented by CUDA.
Stars: ✭ 32 (-70.91%)
Mutual labels:  stereo-vision, stereo-matching
stereo-vision-fpga
Real-time binocular stereo vision FPGA system with OV5640 cameras
Stars: ✭ 20 (-81.82%)
Mutual labels:  stereo-vision
Comparison-of-Disparity-Estimation-Algorithms
Implementation of simple block matching, block matching with dynamic programming and Stereo Matching using Belief Propagation algorithm for stereo disparity estimation
Stars: ✭ 46 (-58.18%)
Mutual labels:  stereo-vision
Semantic-Mono-Depth
Geometry meets semantics for semi-supervised monocular depth estimation - ACCV 2018
Stars: ✭ 98 (-10.91%)
Mutual labels:  stereo-vision
zed-oculus
ZED Viewer for Oculus Rift
Stars: ✭ 27 (-75.45%)
Mutual labels:  stereo-vision
Unsupervised-Adaptation-for-Deep-Stereo
Code for "Unsupervised Adaptation for Deep Stereo" - ICCV17
Stars: ✭ 59 (-46.36%)
Mutual labels:  stereo-vision
sparse-scene-flow
This repo contains C++ code for sparse scene flow method.
Stars: ✭ 23 (-79.09%)
Mutual labels:  stereo-vision
IRONSIDES
Trifo Ironsides SDK
Stars: ✭ 17 (-84.55%)
Mutual labels:  stereo-vision
Reversing
Code for "Reversing the cycle: self-supervised deep stereo through enhanced monocular distillation"
Stars: ✭ 43 (-60.91%)
Mutual labels:  stereo-matching
RoboVision
Attempting to create a program capable of combining stereo video input , with motors and other sensors on a PC running linux , the target is embedded linux for use in a robot!
Stars: ✭ 21 (-80.91%)
Mutual labels:  stereo-vision
StereoVisionforADAS
Stereo vision based object detection for ADAS, autonomous vehicle
Stars: ✭ 137 (+24.55%)
Mutual labels:  stereo-vision
mobilestereonet
Lightweight stereo matching network based on MobileNet blocks
Stars: ✭ 92 (-16.36%)
Mutual labels:  stereo-vision
DispNet-TensorFlow
TensorFlow implementation of DispNet by Zhijian Jiang.
Stars: ✭ 55 (-50%)
Mutual labels:  stereo-vision

Attention-Aware Feature Aggregation for Real-time Stereo Matching on Edge Devices

This repository contains the code (in PyTorch) for "Attention-Aware Feature Aggregation for Real-time Stereo Matching on Edge Devices" paper (ACCV 2020) by Jia-Ren Chang, Pei-Chun Chang and Yong-Sheng Chen.

The codes mainly bring from PSMNet.

Citation

@InProceedings{Chang_2020_ACCV,
    author    = {Chang, Jia-Ren and Chang, Pei-Chun and Chen, Yong-Sheng},
    title     = {Attention-Aware Feature Aggregation for Real-time Stereo Matching on Edge Devices},
    booktitle = {Proceedings of the Asian Conference on Computer Vision (ACCV)},
    month     = {November},
    year      = {2020}
}

Train

As an example, use the following command to train a RTStereo on Scene Flow

python main.py --maxdisp 192 \
               --model RTStereoNet \
               --datapath (your scene flow data folder)\
               --epochs 10 \
               --loadmodel (optional)\
               --savemodel (path for saving model)

Pretrained Model

KITTI 2015 Pretrained Model Google Drive

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].