Sewon Myung

Sewon Myung

Computational Media student @ GT

Posts by Tags

Computer Vision

Exploring 3D Reconstruction Methods: Single-Image 3D Generation

4 minute read

Published:

Reconstructing 3D models from 2D images has long been a fundamental challenge in computer vision and graphics. While traditional methods rely on multi-view geometry to infer depth and structure, recent advances in neural implicit representations and diffusion models have enabled promising approaches for single-image 3D reconstruction. This blog post explores key methodologies, including NeRF-based techniques, One-2-3-45, Adobe’s Large Reconstruction Model (LRM), and Latent NeRF, evaluating their strengths and limitations in the context of single-image 3D generation.

AI Art Critic Documentation

4 minute read

Published:

In my VIP research course, I developed an AI Art Critic, a system designed to provide constructive feedback on both the technical and emotional aspects of artwork. Initially, this project centered around human-computer interaction, allowing artists to refine their work through a text-based chatbot that delivered stylistic critiques. While designing the chatbot’s personality (turning it into a snobbish art critic) and refining the user experience were enjoyable, I soon realized a fundamental limitation: Textual feedback alone was insufficient for technical corrections in areas like anatomy, perspective, and proportion.

Personal

Art and Math to Me

4 minute read

Published:

Growing up, I spent the majority of my time drawing and painting. I drew so much that I would get scolded in school for doodling on my desk. Creating art always felt natural to me–I liked the intuitive nature of it. Everything I needed to learn was right in front of me. Just by observing the world more closely, you can pick up techniques the same way the old masters like Michelangelo and Da Vinci did. In fact, Da Vinci spent most of his time studying nature, searching for patterns to elevate his paintings. Being a good artist also means being a keen observer and thinker.

Project

Exploring 3D Reconstruction Methods: Single-Image 3D Generation

4 minute read

Published:

Reconstructing 3D models from 2D images has long been a fundamental challenge in computer vision and graphics. While traditional methods rely on multi-view geometry to infer depth and structure, recent advances in neural implicit representations and diffusion models have enabled promising approaches for single-image 3D reconstruction. This blog post explores key methodologies, including NeRF-based techniques, One-2-3-45, Adobe’s Large Reconstruction Model (LRM), and Latent NeRF, evaluating their strengths and limitations in the context of single-image 3D generation.

AI Art Critic Documentation

4 minute read

Published:

In my VIP research course, I developed an AI Art Critic, a system designed to provide constructive feedback on both the technical and emotional aspects of artwork. Initially, this project centered around human-computer interaction, allowing artists to refine their work through a text-based chatbot that delivered stylistic critiques. While designing the chatbot’s personality (turning it into a snobbish art critic) and refining the user experience were enjoyable, I soon realized a fundamental limitation: Textual feedback alone was insufficient for technical corrections in areas like anatomy, perspective, and proportion.

Projects

Computational Design

1 minute read

Published:

In a previous post, I mentioned that I first got into programming through art, where I tried to create patterns through lines and curves on my computer. It’s called parametric or generative art, where you give some parameters and variables that can be changed to systemetically create visual images.

Research

Computational Design

1 minute read

Published:

In a previous post, I mentioned that I first got into programming through art, where I tried to create patterns through lines and curves on my computer. It’s called parametric or generative art, where you give some parameters and variables that can be changed to systemetically create visual images.

Exploring 3D Reconstruction Methods: Single-Image 3D Generation

4 minute read

Published:

Reconstructing 3D models from 2D images has long been a fundamental challenge in computer vision and graphics. While traditional methods rely on multi-view geometry to infer depth and structure, recent advances in neural implicit representations and diffusion models have enabled promising approaches for single-image 3D reconstruction. This blog post explores key methodologies, including NeRF-based techniques, One-2-3-45, Adobe’s Large Reconstruction Model (LRM), and Latent NeRF, evaluating their strengths and limitations in the context of single-image 3D generation.

AI Art Critic Documentation

4 minute read

Published:

In my VIP research course, I developed an AI Art Critic, a system designed to provide constructive feedback on both the technical and emotional aspects of artwork. Initially, this project centered around human-computer interaction, allowing artists to refine their work through a text-based chatbot that delivered stylistic critiques. While designing the chatbot’s personality (turning it into a snobbish art critic) and refining the user experience were enjoyable, I soon realized a fundamental limitation: Textual feedback alone was insufficient for technical corrections in areas like anatomy, perspective, and proportion.