gracejary Goto Github PK

occlusion_net

Occlusion-Net: 2D/3D Occluded Keypoint Localization Using Graph Networks

opencv-object-detection

:camera:Object detection with OpenCV on Java. DNN, HaarCascade, Template Matching, Color Detection etc.

paperweekly

Papers for CNN, object detection, keypoint detection, semantic segmentation, AutoML etc.

pcl-ros-cluster-segmentation

Cluster based segmentation of Point Cloud with PCL lib in ROS

physim-dataset-generator

generate physically realistic synthetic dataset of cluttered scenes using 3D CAD models to train CNN based object detectors

pickpack

A ROS package for autonomous thin objects bin picking, specifically pharmaceutical blister packs, with UR10 robotic arm and Robotiq 2-Finger 140mm Adaptive Parallel-jaw gripper.

pix2pose

Original implementation of the paper "Pix2Pose: Pix2Pose: Pixel-Wise Coordinate Regression of Objects for 6D Pose Estimation", in ICCV 2019, https://arxiv.org/abs/1908.07433

pose-interpreter-networks

Code release for "Real-Time Object Pose Estimation with Pose Interpreter Networks"

posefromkeypoints

An implementation of 6 DoF pose from semantic keypoints

posefromshape

(BMVC 2019) PyTorch implementation of Paper "Pose from Shape: Deep Pose Estimation for Arbitrary 3D Objects"

pvnet

Code for "PVNet: Pixel-wise Voting Network for 6DoF Pose Estimation" CVPR 2019 oral

pvnet-rendering

render images for pvnet training

pytorch-3d

Stacked hourglass with linear 3D model

pytorch-keypoint-detection

Pytorch FPN+ResNet+MaskRCNN Keypoint Detection

pytorch-yolo-v3

A PyTorch implementation of the YOLO v3 object detection algorithm

pytorch-yolov3

Minimal PyTorch implementation of YOLOv3

pytorch_yolov3

Implementation of YOLOv3 in PyTorch

recent-stars-2019

:star: SLAM, Pose/Object tracking, Depth/Disparity/Flow Estimation, 3D-graphic, etc. related papers and code

reppoints

Represent Visual Objects by Point Sets

rgbd360

This project integrates the functionality to do image acquisition, localization and mapping using an omnidirectional RGB-D sensor developed in INRIA Sophia-Antipolis by the team LAGADIC, and with the collaboration of the University of Malaga. This functionality comprises: reading and serializing the data streaming from the omnidirectional RGB-D sensor; registering frames based on a compact planar description of the scene (http://www.mrpt.org/pbmap); loop closure detection; performing human-guided semi-automatic labelization of the scene; PbMap-based hybrid SLAM (i.e. using metric-topological-semantic information) with the omnidirectional RGB-D sensor moving freely with 6 DoF, or in planar movement with 3 DoF. Also, some visualization tools are provided to show the results from the above applications.

rgbd_graph_segmentation

Felzenszwalb and Huttenlocher's graph-based image segmentation algorithm, extended to use depth data in various ways

robond-perception-project

Perception Pipeline Linked to a PR2 Robot Picking Objects and Placing in Bins

segmentation-driven-pose

Segmentation-driven 6D Object Pose Estimation. CVPR 2019.

shapematchinggan

[ICCV 2019, Oral] Controllable Artistic Text Style Transfer via Shape-Matching GAN

singleshotpose

This research project implements a real-time object detection and pose estimation method as described in the paper, Tekin et al. "Real-Time Seamless Single Shot 6D Object Pose Prediction", CVPR 2018. (https://arxiv.org/abs/1711.08848).

snake

Code for "Deep Snake for Real-Time Instance Segmentation"

sp_segmenter

Superpixel-based semantic segmentation, with object pose estimation and tracking. Provided as a ROS package.

spherical_regression

PyTorch implementation of cvpr2019 paper "Spherical Regression: Learning Viewpoints, Surface Normals and 3D Rotations on n-Spheres".

ssd-6d

Inference code and trained networks for SSD-6D

stevenlei2017-ai_projects