egeozsoy

RaDialog

Official code for the Paper "RaDialog: A Large Vision-Language Model for Radiology Report Generation and Conversational Assistance"

Xplainer

Official repository for the paper "Xplainer: From X-Ray Observations to Explainable Zero-Shot Diagnosis"

EndoViT

Large-scale Self-supervised Pre-training for Endoscopy

4D-OR

Official code of the paper 4D-OR: Semantic Scene Graphs for OR Domain Modeling accepted at MICCAI 2022. This repo includes both the dataset and our code.

DotsAndBoxesAi

AI for playing Dots and Boxes with Reinforcement Learning

LABRAD-OR

Official code of the paper LABRAD-OR: Lightweight Memory Scene Graphs for Accurate Bimodal Reasoning in Dynamic Operating Rooms accepted at MICCAI 2023.

LF-SGG

Official implementation of Pix2SG, the first location-free scene graph generation method, as well as the corresponding heuristic tree search-based evaluation implemented in C++.

ORacle

Official code of the paper ORacle: Large Vision-Language Models for Knowledge-Guided Holistic OR Domain Modeling accepted at MICCAI 2024.

RawEdit

Edit raw photos with ios/ swift

RawLapse

egeozsoy/4D-OR

Official code of the paper 4D-OR: Semantic Scene Graphs for OR Domain Modeling accepted at MICCAI 2022. This repo includes both the dataset and our code.

egeozsoy/ORacle

Official code of the paper ORacle: Large Vision-Language Models for Knowledge-Guided Holistic OR Domain Modeling accepted at MICCAI 2024.

egeozsoy/LABRAD-OR

Official code of the paper LABRAD-OR: Lightweight Memory Scene Graphs for Accurate Bimodal Reasoning in Dynamic Operating Rooms accepted at MICCAI 2023.

egeozsoy/LF-SGG

Official implementation of Pix2SG, the first location-free scene graph generation method, as well as the corresponding heuristic tree search-based evaluation implemented in C++.

egeozsoy/DotsAndBoxesAi

AI for playing Dots and Boxes with Reinforcement Learning

egeozsoy/3DSSG

egeozsoy/3RScan

3RScan Toolkit

egeozsoy/adversarial_examples_that_fool_classic_computer_vision_methods

egeozsoy/All_The_Right_Measures

egeozsoy/Applying-SlowFast-networks-to-video-object-segmentation

egeozsoy/cpp-constraint

egeozsoy/autosubtitle

Uses whisper to automatically create subtitles for a video.

egeozsoy/cpp-chess

egeozsoy/DVIS_Plus

egeozsoy/EDU4SDS23_Human_Pose_Estimation_in_the_OR

egeozsoy/EndoViT

Large-scale Self-supervised Pre-training for Endoscopy

egeozsoy/fishervector

Improved Fisher Vector Implementation

egeozsoy/hi-ml

HI-ML toolbox for deep learning for medical imaging and Azure integration

egeozsoy/ImagePatcher

egeozsoy/master_lectures_csp

egeozsoy/master_lectures_csp_python

egeozsoy/MiDaS

Code for robust monocular depth estimation described in "Ranftl et. al., Towards Robust Monocular Depth Estimation: Mixing Datasets for Zero-shot Cross-dataset Transfer, TPAMI 2020"

egeozsoy/Mole_cancer_detection

egeozsoy/Open-Assistant

OpenAssistant is a chat-based assistant that understands tasks, can interact with third-party systems, and retrieve information dynamically to do so.

egeozsoy/open_spiel

OpenSpiel is a collection of environments and algorithms for research in general reinforcement learning and search/planning in games.

egeozsoy/Point-BERT

Pre-Training 3D Point Cloud Transformers with Masked Point Modeling

egeozsoy/point-transformer

This is an unofficial implementation of the Point Transformer paper.

egeozsoy/Point-Transformers

Point Transformers

egeozsoy/SecondBrain

egeozsoy/Segment-and-Track-Anything

An open-source project dedicated to tracking and segmenting any objects in videos, either automatically or interactively. The primary algorithms utilized include the Segment Anything Model (SAM) for key-frame segmentation and Associating Objects with Transformers (AOT) for efficient tracking and propagation purposes.