Scholar
Dongki Jung
Google Scholar ID: MEwO0QwAAAAJ
University of Maryland
Citations & Impact
Citations
146
H-index
6
i10-index
4
Publications
15
Co-authors
3
list available
Publications
Resume (English only)
Academic Achievements
- - Preprints:
- * MoRe: Monocular Geometry Refinement via Graph Optimization for Cross-View Consistency
- * UAV4D: Dynamic Neural Rendering of Human-Centric UAV Imagery using Gaussian Splatting
- * UAVTwin: Neural Digital Twins for UAVs using Gaussian Splatting
- * Mode-GS: Monocular Depth Guided Anchored 3D Gaussian Splatting for Robust Ground-View Scene Rendering
- - Publications:
- * RPG360: Robust 360 Depth Estimation with Perspective Foundation Models and Graph Optimization (NeurIPS, 2025)
- * IM360: Large-scale Indoor Mapping with 360 Cameras (ICCV, 2025)
- * EDM: Equirectangular Projection-Oriented Dense Kernelized Feature Matching (CVPR, 2025)
- * WayIL: Image-based Indoor Localization with Wayfinding Maps (ICRA, 2024)
- * TMO: Textured Mesh Acquisition of Objects with a Mobile Device by using Differentiable Rendering (CVPR, 2023)
- * SelfTune: Metrically Scaled Monocular Depth Estimation through Self-Supervised Learning (ICRA, 2022)
Research Experience
- - Currently a second-year Ph.D. student in Computer Science at the University of Maryland, College Park, working in the GAMMA Lab under Prof. Dinesh Manocha.
- - At UMD, worked on 3D reconstruction and neural rendering.
- - Previously, was a research scientist at NAVER LABS, focusing on visual localization and mapping for robotics.
Education
- - Master's Degree: KAIST, Advisor: Changick Kim
- - Bachelor's Degree: Korea University
Background
- Research Interests: 3D multi-view foundation models, combining classical geometry with modern deep learning methods to advance 3D vision.
Miscellany
- Contact: jdk9405@umd.edu | jdk9405@gmail.com
