Gyeongjin Kang

I am currently a research assistant at Yonsei University. Previously, I was an MS student (2024.03 ~ 2026.02) at Sungkyunkwan University. I have broad interests in Computer Vision. My current focus is on (1) self-supervised geometric perception, (2) multimodal representation learning for spatial understanding, and (3) scalable perception from continuous streams for embodied and real-world applications.

Google Scholar GitHub Email

News

Sep 2026Two papers accepted to NeurIPS 2026.
Feb 2026Three papers accepted to CVPR 2026.

Show older news

Feb 2025Two papers accepted to CVPR 2025.
Dec 2024CodecNeRF accepted to AAAI 2025.

Publications

* equal contribution or advising · † corresponding author

Coming soon

3D Consistency Tokens

Seungtae Nam*, Jungwoo Kim*, Gyeongjin Kang, Younggeun Lee, Seungkwon Yang, Eunbyung Park†

NeurIPS 2026

Coming soon

U-MVP: Encode Locally, Decode Globally for Feed-Forward 3D Gaussian Splatting

Seungkwon Yang*, Gyeongjin Kang*, Hwasik Jeong, Byeongjin Kang, Hyeongbhin Cho, Eunbyung Park†

NeurIPS 2026

Rethinking Asymmetry in Self-Supervised 3D Geometry Learning

Gyeongjin Kang, Freeman Cheng, Botao Ye, Weijie Lyu, Ming-Hsuan Yang†, Eunbyung Park†

arXiv 2026

ProjectPaper (coming soon)Code

FineSplat: Fine Patches, Local Groups, Detailed Splats

Hyebin Kim*, Hwasik Jeong*, Joonhyuk Park, Gyeongjin Kang, Jungwoo Kim, Younghyun Kim, Eunbyung Park†

arXiv 2026

Project Paper Code

2Xplat: Two Experts Are Better Than One Generalist

Hwasik Jeong*, Seungryong Lee*, Gyeongjin Kang, Seungkwon Yang, Xiangyu Sun, Seungtae Nam, Eunbyung Park†

arXiv 2026

Project Paper Code

OpenMonoGS-SLAM: Monocular Gaussian Splatting SLAM with Open-set Semantics

Jisang Yoo, Gyeongjin Kang, Hyunkyu Ko, Eunbyung Park†

arXiv 2025

Project Paper

Multi-view Pyramid Transformer: Look Coarser to See Broader

Gyeongjin Kang*, Seungkwon Yang*, Seungtae Nam, Younggeun Lee, Jungwoo Kim, Eunbyung Park†

CVPR 2026

Project Paper Code

Uni3R: Unified 3D Reconstruction and Semantic Understanding via Generalizable Gaussian Splatting from Unposed Multi-View Images

Xiangyu Sun*, Haoyi Jiang*, Liu Liu, Seungtae Nam, Gyeongjin Kang, Xinjie Wang, Wei Sui, Zhizhong Su, Wenyu Liu, Xinggang Wang, Eunbyung Park†

CVPR 2026 (Highlight)

Project Paper Code

iLRM: An Iterative Large 3D Reconstruction Model

Gyeongjin Kang, Seungtae Nam, Xiangyu Sun, Semah Khamis, Abdelrahman Mohamed, Eunbyung Park†

CVPR 2026

Project Paper Code

Generative Densification: Learning to Densify Gaussians for High-Fidelity Generalizable 3D Reconstruction

Seungtae Nam*, Xiangyu Sun*, Gyeongjin Kang, Younggeun Lee, Seungjun Oh, Eunbyung Park†

CVPR 2025 (Highlight)

Project Paper Code

SelfSplat: Pose-Free and 3D Prior-Free Generalizable 3D Gaussian Splatting

Gyeongjin Kang*, Jisang Yoo*, Jihyeon Park, Seungtae Nam, Hyeonsoo Im, Sangheon Shin, Sangpil Kim, Eunbyung Park†

CVPR 2025

Project Paper Code

CodecNeRF: Toward Fast Encoding and Decoding, Compact, and High-quality Novel-view Synthesis

Gyeongjin Kang*, Younggeun Lee*, Seungjun Oh, Eunbyung Park†

AAAI 2025

Project Paper Code