Geonung Kim

I am currently a Ph.D. candidate at POSTECH, researching as a member of the Computer Graphics Lab under the supervision of Prof. Sunghyun Cho.

My research broadly explores generative models, and I am especially interested in generating and understanding 3D worlds, a direction I am actively pursuing in my current work.

Geonung Kim

News

Publications

HL-OutPaint: High-Resolution Long-Range Video Outpainting with a Global Coarse Scaffold

HL-OutPaint: High-Resolution Long-Range Video Outpainting with a Global Coarse Scaffold

Jeongeun Park, Janghyeok Han, Geonung Kim, Hyun-Seung Lee, Kyuha Choi, Youngseok Han, Sunghyun Cho

Accepted to SIGGRAPH Conference, 2026

VideoFrom3D: 3D Scene Video Generation via Complementary Image and Video Diffusion Models

VideoFrom3D: 3D Scene Video Generation via Complementary Image and Video Diffusion Models

Geonung Kim, Janghyeok Han, Sunghyun Cho

Accepted to SIGGRAPH Asia Conference, 2025

Page Paper arXiv Code
DC-VSR: Spatially and Temporally Consistent Video Super-Resolution with Video Diffusion Prior

DC-VSR: Spatially and Temporally Consistent Video Super-Resolution with Video Diffusion Prior

Janghyeok Han, Gyujin Sim, Geonung Kim, Hyun-Seung Lee, Kyuha Choi, Youngseok Han, Sunghyun Cho

Accepted to SIGGRAPH Conference, 2025

Page
LayeringDiff: Layered Image Synthesis via Generation, then Disassembly with Generative Knowledge

LayeringDiff: Layered Image Synthesis via Generation, then Disassembly with Generative Knowledge

Kyoungkook Kang, Gyujin Sim, Geonung Kim, Donguk Kim, Seungho Nam, Sunghyun Cho

arXiv, 2025

arXiv
RNA: Video Editing with ROI-based Neural Atlas

RNA: Video Editing with ROI-based Neural Atlas

Jaekyeong Lee*, Geonung Kim*, Sunghyun Cho

Accepted to Asian Conference on Computer Vision (ACCV), 2024

Page Code
Diffusion Model Compression for Image-to-Image Translation

Diffusion Model Compression for Image-to-Image Translation

Geonung Kim, Beomsu Kim, Eunhyeok Park, Sunghyun Cho

Accepted to Asian Conference on Computer Vision (ACCV), 2024

Page Paper Code
360 Reconstruction From a Single Image Using Space Carved Outpainting

360 Reconstruction From a Single Image Using Space Carved Outpainting

Nuri Ryu, Minsu Gong, Geonung Kim, Joo-Haeng Lee, Sunghyun Cho

Accepted to SIGGRAPH Asia Conference, 2023

Code
BigColor: Colorization using a Generative Color Prior for Natural Images

BigColor: Colorization using a Generative Color Prior for Natural Images

Geonung Kim, Kyoungkook Kang, Seongtae Kim, Hwayoon Lee, Sehoon Kim, Jonghyun Kim, Seung-Hwan Baek, Sunghyun Cho

Accepted to European Conference on Computer Vision (ECCV), 2022

Page Paper Code
Realistic Blur Synthesis for Learning Image Deblurring

Realistic Blur Synthesis for Learning Image Deblurring

Jaesung Rim, Geonung Kim, Jungeon Kim, Junyong Lee, Seungyong Lee, Sunghyun Cho

Accepted to European Conference on Computer Vision (ECCV), 2022

Page Code
DynaGAN: Dynamic Few-shot Adaptation of GANs to Multiple Domains

DynaGAN: Dynamic Few-shot Adaptation of GANs to Multiple Domains

Seongtae Kim, Kyoungkook Kang, Geonung Kim, Seung-Hwan Baek, Sunghyun Cho

Accepted to SIGGRAPH Asia Conference, 2022

Code
Dr.3D: Adapting 3D GANs to Artistic Drawings

Dr.3D: Adapting 3D GANs to Artistic Drawings

Wonjoon Jin, Nuri Ryu, Geonung Kim, Seung-Hwan Baek, Sunghyun Cho

Accepted to SIGGRAPH Asia Conference, 2022

Page Code