Language Translation Software Development
Published:
Developed a full-stack web application with AI-powered language translation, supporting 50+ languages, and enhanced chatbot conversational flows.
Posts by Collection
projects
Night Walker with Raspberry Pi-Controlled Viam Rover
Published:
Developed an autonomous robot equipped with a TensorFlow Lite model for object detection and navigation in low-light environments.
Machine Learning and NLP for Sentiment Analysis in Transformative Music
Published:
Analyzed lyrical and musical elements using machine learning and NLP to predict emotional impacts of transformative music.
Unity ML-Agents with Walking Robot using Curriculum Training
Published:
Developed a phased curriculum training approach to enhance AI walking and navigation in complex environments using Unity ML-Agents.
publications
CSG-Based ML-Supported 3D Translation of Sketches into Game Assets
Published in The Visual Computer, 2025
This paper introduces a system that translates freehand 2D sketches into detailed 3D models using Constructive Solid Geometry (CSG) and machine learning techniques.
Recommended citation: Chen, Y., Liu, Y., & Kayar-Ceylan, G. (2025). "CSG-based ML-supported 3D translation of sketches into game assets for game designers." Visual Computer. https://doi.org/10.1007/s00371-024-03758-9
Download Paper
researches
CSG-Based ML-Supported 3D Translation of Sketches into Game Assets
Published:
Developed algorithms to convert hand-drawn sketches into 3D assets using Constructive Solid Geometry (CSG).
Recommended citation: Chen, Y., Liu, Y., & Kayar-Ceylan, G. (2025). "CSG-based ML-supported 3D translation of sketches into game assets for game designers." Visual Computer. https://doi.org/10.1007/s00371-024-03758-9
Gaussian Visibility Field for Uncertainty Mapping
Published:
Developed the Gaussian Visibility Field (GVF) using deep learning techniques for uncertainty mapping, achieving 80% faster rendering compared to Neural Visibility Field.
Recommended citation: Under development
Diffusion-Based Concept Generation for Machine Learning Models
Published:
Developed advanced diffusion models for hybrid and part-based concept generation with integrated NLP guidance and ControlNet-based segmentation.
Recommended citation: Under development