Scholar
Jongmin Park
Google Scholar ID: PWio4eYAAAAJ
KAIST
Citations & Impact
Citations
171
H-index
4
i10-index
2
Publications
6
Co-authors
6
list available
Publications
Resume (English only)
Academic Achievements
- Preprints: 'MoBGS: Motion Deblurring Dynamic 3D Gaussian Splatting for Blurry Monocular Video'. Publications: 'MoBluRF: Motion Deblurring Neural Radiance Fields for Blurry Monocular Video' accepted in TPAMI, 'SplineGS: Robust Motion-Adaptive Spline for Real-Time Dynamic 3D Gaussians from Monocular Video' presented at CVPR, 'COMPASS: High-Efficiency Deep Image Compression with Arbitrary-scale Spatial Scalability' showcased at ICCV. Patents: KR1025639530000 and KR1020240071361. Awards: Best Paper Award (Chang-kyu Park Academic Award) at Korea Institute of Military Science and Technology and Outstanding Paper Award at Korea Institute of Broadcast and Media Engineers, both in June 2023.
Research Experience
- April 2022 - Present: Deep Learning-based Rendering of Spatial Video with Stationary and Dynamic Scenes, supported by SW STAR LAB; Proposed a COLMAP-free dynamic 3D reconstruction framework via motion-adaptive spline deformation of 3D Gaussians. September 2022 – May 2023: AI-based Image Compression with Spatial Scalability, supported by Electronics and Telecommunications Research Institute; Proposed a learned, scalable image compression framework capable of decoding at any arbitrary (non-integer) scale from a single bitstream.
Education
- Ph.D. candidate at the School of Electrical Engineering, KAIST since 09.2022, advised by Prof. Munchurl Kim (VICLAB); M.S. in School of Electrical Engineering, KAIST from 09.2020 to 08.2022, advised by Prof. Munchurl Kim (VICLAB); B.S. in School of Electrical Engineering, KAIST from 03.2015 to 08.2020.
Background
- Research interests include 3D computer vision, novel view synthesis (such as NeRF, Gaussian Splatting), low-level vision, and generative models.
Miscellany
- No detailed information provided about personal interests.
