wulun0102 Goto Github PK

3d-machine-learning

A resource repository for 3D machine learning

3d-vision-and-touch

When told to understand the shape of a new object, the most instinctual approach is to pick it up and inspect it with your hand and eyes in tandem. Here, touch provides high fidelity localized information while vision provides complementary global context. However, in 3D shape reconstruction, the complementary fusion of visual and haptic modalities remains largely unexplored. In this paper, we study this problem and present an effective chart-based approach to fusing vision and touch, which leverages advances in graph convolutional networks. To do so, we introduce a dataset of simulated touch and vision signals from the interaction between a robotic hand and a large array of 3D objects. Our results show that (1) leveraging both vision and touch signals consistently improves single-modality baselines, especially when the object is occluded by the hand touching it; (2) our approach outperforms alternative modality fusion methods and strongly benefits from the proposed chart-based structure; (3) reconstruction quality boosts with the number of grasps provided; and (4) the touch information not only enhances the reconstruction at the touch site but also extrapolates to its local neighborhood.

arena2d

A plattform to ease DRL research

awesome-6d-object

Awesome work on object pose estimation and reconstruction

awesome-embodied-vision

Reading list for research topics in embodied vision

awesome-object-pose

This repository is a curated list of papers and open source code for 6D Object Pose Estimation.

badslam

Bundle Adjusted Direct RGB-D SLAM

benchbot

BenchBot is a tool for seamlessly testing & evaluating semantic scene understanding tools in both realistic 3D simulation & on real robots

blenderproc

A procedural Blender pipeline for photorealistic training image generation

cblox

Voxblox-based submapping

ccm_slam

CCM-SLAM: Robust and Efficient Centralized Collaborative Monocular SLAM for Robotic Teams

ceres-solver

I built a new project and rewrite the slam part including slam_2d and slam_3d

ceres_mono_orb_slam2

ORB SLAM optimization implement with ceres solver

clean-pvnet

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

collisiondetection

A book and examples on collision detection

confusion-matrix-for-mask-r-cnn

Confusion matrix for Mask R-CNN (Matterport implementation)

corb-slam

cosypose

Code for "CosyPose: Consistent multi-view multi-object 6D pose estimation", ECCV 2020.

cubicsdr

Cross-Platform Software-Defined Radio Application

cupoch

Robotics with GPU computing

cvpr2020-code

CVPR 2020 论文开源项目合集

cvtoolbox

计算机视觉——一种现代方法

deep_object_pose

Deep Object Pose Estimation (DOPE) – ROS inference (CoRL 2018)

deepdepthrefiner

Depth map refine using occlusion edge and occlusion order

deepimageblending

This is a Pytorch implementation of deep image blending

deformable-kernels

Deforming kernels to adapt towards object deformation. In ICLR 2020.

densefusion

"DenseFusion: 6D Object Pose Estimation by Iterative Dense Fusion" code repository

densefusion_ros

depthtonormal

Python code used to transform depth map to normal map

dfc2019

2019 IEEE GRSS Data Fusion Contest data, baselines, and metrics