Author: Ekrem Çetinkaya

126 POSTS0 COMMENTS
Ekrem Çetinkaya received his B.Sc. in 2018, and M.Sc. in 2019 from Ozyegin University, Istanbul, Türkiye. He wrote his M.Sc. thesis about image denoising using deep convolutional networks. He received his Ph.D. degree in 2023 from the University of Klagenfurt, Austria, with his dissertation titled "Video Coding Enhancements for HTTP Adaptive Streaming Using Machine Learning." His research interests include deep learning, computer vision, video encoding, and multimedia networking.

Divided We Fall, United We Stand: CoTracker is an AI Approach That Jointly Tracks Multiple Points in a Video

Recent years have been full of advancements in image generation and large language models in the AI domain. They have been under the spotlight...

The AI Cousin of Michelangelo: Neuralangelo is an AI Model That can Achieve High-Fidelity 3D Surface Reconstruction [Code Included]

Neural networks have advanced quite significantly in recent years, and they have found themselves a use case in almost all applications. One of the...

ChatGPT with Eyes and Ears: BuboGPT is an AI Approach That Enables Visual Grounding in Multi-Modal LLMs

Large Language Models (LLMs) have emerged as game changers in the natural language processing domain. They are becoming a key part of our daily...

Tailoring the Fabric of Generative AI: FABRIC is an AI Approach That Personalizes Diffusion Models with Iterative Feedback

Generative AI is a term that we all are familiar with nowadays. They have advanced a lot in recent years and have become a...

The Consistent AI Video Editor Has Arrived: TokenFlow is an AI Model That Uses Diffusion Features for Consistent Video Editing

Diffusion models are something you should be familiar with at this point. They have been the key topic in the AI domain for the...

Put Me in the Center Quickly: Subject-Diffusion is an AI Model That Can Achieve Open Domain Personalized Text-to-Image Generation

Text-to-image models have been the cornerstone of every AI discussion for the last year. The advancement in the field happened quite rapidly, and as...

Not the Hero NeRFs Deserve, but the Hero NeRFs Need: CopyRNeRF is an AI Approach That Protects the Copyright of NeRFs

If you have been paying attention to the development in the computer graphics domain, you should be familiar with neural radiance fields (NeRFs). They...

Deep Learning for Deep Objects: ZoeDepth is an AI Model for Multi-Domain Depth Estimation

Have you ever encountered illusions where a kid in the image looks taller and bigger than an adult? Ames room illusion is a famous...

Could It Be the Patches? This AI Approach Analyzes the Key Contributor to the Success of Vision Transformers

Convolutional neural networks (CNNs) have been the backbone of systems for computer vision tasks. They have been the go-to architecture for all types of...

How Should We Store AI Images? Google Researchers Propose an Image Compression Method Using Score-based Generative Models

A year ago, generating realistic images with AI was a dream. We were impressed by seeing generated faces that resemble real ones, despite the...

Dream First, Learn Later: DECKARD is an AI Approach That Uses LLMs for Training Reinforcement learning (RL) Agents

Reinforcement learning (RL) is a popular approach to training autonomous agents that can learn to perform complex tasks by interacting with their environment. RL...

One Diffusion to Rule Diffusion: Modulating Pre-trained Diffusion Models for Multimodal Image Synthesis

Image generation AI models have stormed the domain in the last couple of months. You probably heard of midjourney, DALL-E, ControlNet, or Stable dDiffusion....

Check Out Our Super Cool AI Research Newsletter While It's Still Free

X