This is the official PyTorch implementation of ShadowRefiner. Our method is winner of Perceptual Track and achieves the second-best performance for Fidelity Track in NTIRE 2024 Shadow Removal Chall…

This project provides a command-line interface for interacting with IBM's Watson AI using the watsonX.ai API. It allows users to engage in conversations with the AI model, supporting both English a…

[CVPR 2024] Official implementation for "Equivariant Multi-Modality Image Fusion."

A high-altitude infrared thermal dataset for Unmanned Aerial Vehicle-based object detection

Accurate trajectory generation and tracking with interface to PX4 autopilot

Python script for system identification and tuning of PX4 PID loops based on PX4 logs (ulog only).

Docker files and scripts to setup and run VINS-FUSION-gpu on NVIDIA jetson boards inside a docker container.

Python implementation of the SDK of SIYI camera-gimbal systems

This package implements methods to enable a PX4-powered multi-rotor to track a moving vehicle.

Integration of Fast-Planner with PX4 autopilot for multi-rotor fast navigation with obstacle avoidance

A ROS package with an implementation of a linear Kalman filter for multi-target state estimation.

Commanding robots using only Language Models' prompts

PyTorch code for our ICLR 2023 paper "Accurate Image Restoration with Attention Retractable Transformer".

This repository categorizes the papers about diffusion models applied in computer vision according to their target task. The classifcation is based on our survey: https://arxiv.org/abs/2209.04747v1

stableKnowledge is a SOTA text-to-image-to-text pipeline to automatically classify terms using attention-based neural networks

remote sensing, hazy dataset, haze removal

Image Restoration with Mean-Reverting Stochastic Differential Equations, ICML 2023. Winning solution of the NTIRE 2023 Image Shadow Removal Challenge.

A Collection of Papers and Datasets for Light Field Image Super-Resolution

Official implementation of paper "MiniGPT-5: Interleaved Vision-and-Language Generation via Generative Vokens"

[ICLR 2024] Fine-tuning LLaMA to follow Instructions within 1 Hour and 1.2M Parameters

DM-AHR: a customized Self-Supervised Diffusion Model for Automatic Hair Removal in Dermoscopic Images for Enhanced skin diagnosis

Generative Diffusion Prior for Unified Image Restoration and Enhancement (CVPR2023)

Code for "Quantized Densely Connected U-Nets for Efficient Landmark Localization" (ECCV 2018) and "CU-Net: Coupled U-Nets" (BMVC 2018 oral)

Transformer-based Multi-Stage Enhancement for Remote Sensing Image Super-Resolution (accepted by TGRS)

Code for instruction-tuning Stable Diffusion.

Kandinsky 2 — multilingual text2image latent diffusion model