The best ChatGPT that $100 can buy.

RF-DETR is a real-time object detection and segmentation model architecture developed by Roboflow, SOTA on COCO and designed for fine-tuning.

This repository contains demos I made with the Transformers library by HuggingFace.

Project AirSim is Microsoft's evolution of AirSim, an advanced simulation platform for building, training, and testing autonomous systems in high-fidelity virtual environments

The official implementation of Error Detection in Egocentric Procedural Task Videos

Code implementation for our ECCV, 2022 paper titled "My View is the Best View: Procedure Learning from Egocentric Videos"

Python program to make LLM agents play characters and talk to each other.

Virtual Try-On FashionGenAI is an AI-powered tool that allows users to visualize themselves in different clothes based on their own images and text prompts. The project utilizes Stable Diffusion In…

Reference PyTorch implementation and models for DINOv3

[ICCV 2025] - Image Intrinsic Scale Assessment: Bridging the Gap Between Quality and Resolution

[ACM Multimedia 2023] Taming the Power of Diffusion Models for High-Quality Virtual Try-On with Appearance Flow.

Virtual Clothing Assistant a custom unique implementation of ViTON, allows user to try different clothings virtually

Visual Drone Detection Dataset for Comprehensive Study of Domain shift

Deep Learning for Event-based Vision: A Comprehensive Survey and Benchmarks

We write your reusable computer vision tools. 💜

[ICCV 2025] Event-based Tiny Object Detection: A Benchmark Dataset and Baseline

FlexTok: Resampling Images into 1D Token Sequences of Flexible Length

🔥[CVPR2025] EventGPT: Event Stream Understanding with Multimodal Large Language Models

[CVPR 2025 Oral] VideoEspresso: A Large-Scale Chain-of-Thought Dataset for Fine-Grained Video Reasoning via Core Frame Selection

Processing Pipeline for Natural Object Dataset (NOD)

All-in-one training for vision models (YOLO, ViTs, RT-DETR, DINOv3): pretraining, fine-tuning, distillation.

FRED: The Florence RGB-Event Drone Dataset

[IEEE TCYB 2023] The first large-scale tracking dataset by fusing RGB and Event cameras.

[CVPR 2025-ADVML] Official Repository for `Attacking Attention of Foundation Models Effectively Disrupts Downstream Tasks`

[CVPR 2025 Highlight] Official repository for the paper: "SAMWISE: Infusing Wisdom in SAM2 for Text-Driven Video Segmentation"

Semantic segmentation with railsem19 conducted in advance to carry out detecting railway-related objects performed by the KRRI.

Our event-based datasets