Journal of the Korea Computer Graphics Society 2025

4 papers
The 2025 edition of the Journal of the Korea Computer Graphics Society focuses on generative modeling, motion synthesis, and image restoration. A primary research direction involves the application of Mixture of Experts (MoE) architectures to improve text-based 3D motion generation. This includes studies on scaling large neural networks via sparse activation and mitigating expert collapse to enhance model specialization. Related work explores representing human motion as a discrete language by decomposing movement into modular body part tokens. The volume also addresses advancements in optical simulation and scene reconstruction. Research includes lens modeling for the integrated simulation of optical image degradation and the development of non-uniform exposure prediction pipelines for burst image restoration. Additionally, the journal features work on 3D indoor scene generation using diffusion models that incorporate user interaction awareness. Prolific contributors for this year include HyeongYeop Kang, Hyoseok Hwang, and Woohyeok Kim. Collectively, these papers demonstrate an emphasis on integrating sparse neural architectures with computer graphics tasks such as rendering and scene synthesis.

Top Research Directions

The 5 research directions with Journal of the Korea Computer Graphics Society 2025 papers, ranked by paper count. Share is the fraction of the edition’s papers in the direction.

#DirectionPapersShare
1Conditional Computation via Sparse Mixture of Experts125.0%
2Discrete Tokenization for Human Motion Modeling125.0%
3Emergent Specialization in Modular Neural Architectures125.0%
4Mitigating Expert Collapse in Sparse Mixture of Experts125.0%
5The Gap Between Visual Sophistication and Functional Logic125.0%

Download all directions as CSV

Institutions

Institutions credited by Journal of the Korea Computer Graphics Society 2025 papers: a paper credits every institution named in its affiliations, once. 3 institutions share 2 credited papers.

#InstitutionPapersShare
1Korea University 2100.0%
2Kyung Hee University 2100.0%
3Government of the Republic of Korea 150.0%

Download all institutions as CSV

About this data

Papers. Journal of the Korea Computer Graphics Society 2025 lists 4 papers on Lacuna, duplicate versions counted once; rejected and withdrawn submissions are left out.

Directions. Directions are Lacuna’s clustering of the concept elements extracted from each paper, so a paper can belong to several and direction counts add up to more than the paper count. A direction’s share is its papers divided by the edition’s papers.

Institutions. A paper credits each institution named in its affiliations, resolved to a ROR record, once. 2 of 4 papers (50.0%) credit at least one institution and are the base for institution shares; the rest have no resolved affiliation yet.

Data. Counts come from Lacuna’s data build of 2026-11-19 and change as papers are added. Tables as CSV: directions · institutions. Cite as: Lacuna, “Journal of the Korea Computer Graphics Society 2025”, https://lacuna.tiptreesystems.com/venue/journal-of-the-korea-computer-graphics-society/2025.

Top Authors

AuthorPapers
Hyoseok Hwang2
HyeongYeop Kang1

Papers

Title
3D Indoor Scene Generation via Diffusion with User Interaction Awareness
Lens Modeling for Integrated Simulation of Optical Image Degradation
Non-uniform Exposure Prediction Pipeline for Burst Image Restoration
Text-based 3D Motion Generation with a Mixture of Experts for Enhancing Performance