leob03

2Stage_Object_Detector

A two-stage object detector, based on Faster R-CNN, which consists of two modules - Region Proposal Networks (RPN) and Fast R-CNN. Trained to detect a set of object classes and evaluate the detection accuracy using the classic metric mean Average Precision (mAP).

E2E_Object_Pose_Estimator

Implementation of an end-to-end object pose estimator, based on PoseCNN, which consists of two stages - feature extraction with a backbone network and pose estimation represented by instance segmentation, 3D translation estimation, and 3D rotation estimation.

HisRepItself

HRC_extrinsic_calib

Extrinsic calibration on ROS of the Human Pose Estimation body joints performed from an Azure Kinect with a Collaborative Industrial robot in the context of Human Robot Collaboration (HRC).

human_motion_forecasting

Human Motion Forecasting in the context of Dynamic Human-Robot Collaboration using GCNs, LSTMs and Self-Attention.

Image_captioning

Implementation of neural network model that can generate natural language captions for images. Three different architectures are proposed and compared: first one uses vanilla recurrent neural networks (RNNs), second one long-short term memory networks (LSTMs), and third one attention-based LSTMs.

mdmp

Official PyTorch Implementation of: "MDMP: Multi-modal Diffusion for supervised Motion Predictions"

PointNet_Self_Attention

Improving PointNet through the use of Self-Attention Layers to combine overall with fine-grained features.

PTAE

A Point Transformer based Auto-Encoder for Robot Grasping and Grasping Candidate Quality Inference.

Style_Transfer

Implementation of an Image Style Transfer Neural Network

leob03/human_motion_forecasting

Human Motion Forecasting in the context of Dynamic Human-Robot Collaboration using GCNs, LSTMs and Self-Attention.

leob03/E2E_Object_Pose_Estimator

Implementation of an end-to-end object pose estimator, based on PoseCNN, which consists of two stages - feature extraction with a backbone network and pose estimation represented by instance segmentation, 3D translation estimation, and 3D rotation estimation.

leob03/PointNet_Self_Attention

Improving PointNet through the use of Self-Attention Layers to combine overall with fine-grained features.

leob03/PTAE

A Point Transformer based Auto-Encoder for Robot Grasping and Grasping Candidate Quality Inference.

leob03/Image_captioning

Implementation of neural network model that can generate natural language captions for images. Three different architectures are proposed and compared: first one uses vanilla recurrent neural networks (RNNs), second one long-short term memory networks (LSTMs), and third one attention-based LSTMs.

leob03/2Stage_Object_Detector

A two-stage object detector, based on Faster R-CNN, which consists of two modules - Region Proposal Networks (RPN) and Fast R-CNN. Trained to detect a set of object classes and evaluate the detection accuracy using the classic metric mean Average Precision (mAP).

leob03/HRC_extrinsic_calib

Extrinsic calibration on ROS of the Human Pose Estimation body joints performed from an Azure Kinect with a Collaborative Industrial robot in the context of Human Robot Collaboration (HRC).

leob03/mdmp

Official PyTorch Implementation of: "MDMP: Multi-modal Diffusion for supervised Motion Predictions"

leob03/Style_Transfer

Implementation of an Image Style Transfer Neural Network

leob03/HisRepItself

leob03/mavros-delivery-drone

Delivery Drone build with PX4 and Mavros

leob03/biological_networks

Mathematics of Biological Networks

leob03/block_detection_armlab

leob03/ComfyUI

The most powerful and modular stable diffusion GUI, api and backend with a graph/nodes interface.

leob03/denoising-diffusion-pytorch

Implementation of Denoising Diffusion Probabilistic Model in Pytorch

leob03/flux

Official inference repo for FLUX.1 models

leob03/HumanML3D

HumanML3D: A large and diverse 3d human motion-language dataset.

leob03/leob03

Config files for my GitHub profile.

leob03/MotionGPT

[NeurIPS 2023] MotionGPT: Human Motion as a Foreign Language, a unified motion-language generation model using LLMs

leob03/openpose

OpenPose: Real-time multi-person keypoint detection library for body, face, hands, and foot estimation

leob03/ROB-590

iiwa pose estimation

leob03/slam_autonomy

This repo contains the SLAM and motion controller of our mbot.

leob03/x-flux

leob03/x-flux-comfyui

More elaborate sampling for rectified flow models