Pytorch implementation of Hebbian learning algorithms to train deep convolutional neural networks.

[ECCV 2024] WiMANS: A Benchmark Dataset for WiFi-based Multi-user Activity Sensing

Using of the WiFi signal in combination with deep learning architectures, commonly used in computer vision, to estimate dense human pose correspondence.

Example of "biological" learning for MNIST

A Collection of Variational Autoencoders (VAE) in PyTorch.

Official repo for VDD: Varied Drone Dataset for Semantic Segmentation, published in Journal of Visual Communication and Image Regresentation

This is the official implementation for Knowledge NeRF: Few-shot Novel View Synthesis for Dynamic Articulated Objects

Official implementation of AAAI 2025 paper: Object-level Geometric Structure Preserving for Natural Image Stitching

Reimplementation of GR-1, a generalized policy for robotics manipulation.

The official repo for "SpatialBot: Precise Spatial Understanding with Vision Language Models.

CALVIN - A benchmark for Language-Conditioned Policy Learning for Long-Horizon Robot Manipulation Tasks

[NeurIPS 2023] Official implementation of the paper "Segment Everything Everywhere All at Once"

Grounded SAM: Marrying Grounding DINO with Segment Anything & Stable Diffusion & Recognize Anything - Automatically Detect , Segment and Generate Anything

Pytorch implementation of the models RT-1-X and RT-2-X from the paper: "Open X-Embodiment: Robotic Learning Datasets and RT-X Models"

A curated list of papers and resources related to Described Object Detection, Open-Vocabulary/Open-World Object Detection and Referring Expression Comprehension. Updated frequently and pull request…

DROID Policy Learning and Evaluation

Official Algorithm Implementation of ICML'23 Paper "VIMA: General Robot Manipulation with Multimodal Prompts"

Octo is a transformer-based robot policy trained on a diverse mix of 800k robot trajectories.

Democratization of RT-2 "RT-2: New model translates vision and language into action"

Simulate the iteration of a UR5 robot with Lego bricks

ROS package to simulate UR5 robot using Gazebo and ROS

A family of lightweight multimodal models.

A collection of algorithm pipelines for segmentation of aerial imagery implemented by PyTorch.

Large-Scale Structure from Motion with Semantic Constraints of Aerial Images, PRCV 2018