Author: Ekrem Çetinkaya

88 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 is currently pursuing a Ph.D. degree at the University of Klagenfurt, Austria, and working as a researcher on the ATHENA project. His research interests include deep learning, computer vision, and multimedia networking.

Take My Video to Another Dimension: HOSNeRF is an AI Model That Can Generate Dynamic Neural Radiance Fields from a Single Video

We’ve experienced that Immersive media is becoming a hot topic recently thanks to the advancements in 3D reconstruction methods. Especially video reconstruction and free-viewpoint...

Instant Cameras, Evolved: This Text-to-Image AI Model Can Be Personalized Quickly with Your Images

Text-to-image generation is a term we are all familiar with at this point. The era after the stable diffusion release has brought another meaning...

When SAM Meets NeRF: This AI Model Can Segment Anything in 3D

We are all amazed by the generative AI advancements recently, but that does not mean we do not get any significant breakthroughs in other...

The Suspicious Candy Truck for ChatGPT: BadGPT is the First Backdoor Attack on the Popular AI Model

ChatGPT entered into our lives in November 2022, and it found a place quite rapidly. It had one of the fastest-growing user bases in...

Agents, Assemble! Meet AutoNeRF: An AI Approach Designed to Use Autonomous Agents to Generate Implicit Scene NeRFs

Drones and robots. They are becoming increasingly popular in recent years, with advances in technology making them more accessible and capable than ever before....

The AI Sculptor No One Expected: TextMesh is an AI Model That Can  Generate Realistic 3D Meshes From Text Prompts

Generative AI. This is the term in the AI domain recently. Everyone is talking about it, and it keeps getting more and more impressive....

Take Me to Another Dimension: This AI Model Can Generate Realistic Generative 3D Face Models

Generating anything, whether it’s a text or an image, in the digital world has never been easier, thanks to the advancement of neural networks...

Divide, Train, and Generate: Patch Diffusion is an AI Approach to Make Training Diffusion Models Faster and More Data-Efficient

Image generation has come a long way in the last year. The saga began with the release of Stable Diffusion, and its success has...

Forget Haaland, We Have a New Wonderkid: This AI Approach Trains a Bipedal Robot with Deep RL to Teach Agile Football Skills

Robots have come a long way since their inception. They turned from simple automated machines to highly sophisticated, artificially intelligent things that can now...

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...

Metrics Can Deceive, but Eyes Can Not: This AI Method Proposes a Perceptual Quality Metric for Video Frame Interpolation

The advancement in display technology has made our viewing experience more intense and pleasant. Watching something in 4K 60FPS is extremely satisfying than 1080P...

Moving Images with No Effort: Text2Video-Zero is an AI Model That Converts Text-to-Image Models to Zero-Shot Video Generators

We have witnessed the rise of generative AI models in the last couple of months. They went from generating low-resolution face-like images to generating...

Be the first to know the latest AI research breakthroughs.

X