My Research Topics: Computer Vision and Dynamic 3D World Modeling

Computer Vision Researcher | Ph.D Student

Minh-Quan

About Me

I am a Ph.D. student in Electrical Engineering at VIC Lab, KAIST, under the supervision of Prof. Munchurl Kim. Before that I received my bachelor's degree from Ho Chi Minh City University of Technology-VNU, working with Dr. Duc Dung Nguyen.

My current research focuses on computer vision, neural rendering, and dynamic 3D world reconstruction from casually captured images and videos.

Education

  • Ph.D. in Electrical Engineering KAIST, 2023-Present
  • M.Sc. in Electrical Engineering KAIST, 2022-2023
  • B.Sc. in Computer Science Ho Chi Minh City University of Technology - VNU, 2017-2021

Research Interests

Computer Vision 2D/3D Reconstruction Neural Rendering Deep Learning Computer Graphics

Technical Skills

Python Pytorch/Jax/Tensorflow CUDA/C++

Research Projects

MoBGS: Motion Deblurring Dynamic 3D Gaussian Splatting for Blurry Monocular Video

Deblurring dynamic 3D Gaussian Splatting (3DGS) framework capable of reconstructing sharp and high-quality novel spatio-temporal views from blurry monocular videos in an end-to-end manner.

arXiv 2025

SplineGS: Robust Motion-Adaptive Spline for Real-Time Dynamic 3D Gaussians from Monocular Video

COLMAP-free dynamic 3D Gaussian Splatting (3DGS) framework for high-quality reconstruction and fast rendering from monocular videos.

CVPR 2025

MoBluRF: Motion Deblurring Neural Radiance Fields for Blurry Monocular Video

A novel motion deblurring NeRF framework for blurry monocular video, called MoBluRF.

IEEE Transactions on Pattern Analysis and Machine Intelligence

ProNeRF: Learning Efficient Projection-Aware Ray Sampling for Fine-Grained Implicit Neural Radiance Fields

A projection-aware neural radiance field model, referred to as ProNeRF, which provides an optimal trade-off between the memory footprint, speed, and quality.

IEEE Access

Transfer multi-source knowledge via scale-aware online domain adaptation in depth estimation for autonomous driving

Online monocular depth adaptation model that aims to train an initial depth estimation model in a source domain and continuously adapt the model against a constantly changing target domain.

Image and Vision Computing

Publications

Under Review

MoBGS: Motion Deblurring Dynamic 3D Gaussian Splatting for Blurry Monocular Video

Minh-Quan Viet Bui*, Jongmin Park*, Juan Luis Gonzalez Bello, Jaeho Moon, Jihyong Oh, Munchurl Kim

Conference

SplineGS: Robust Motion-Adaptive Spline for Real-Time Dynamic 3D Gaussians from Monocular Video

Jongmin Park*, Minh-Quan Viet Bui*, Juan Luis Gonzalez Bello, Jaeho Moon, Jihyong Oh, Munchurl Kim

IEEE/CVF Conference on Computer Vision and Pattern Recognition 2025

Journal

MoBluRF: Motion Deblurring Neural Radiance Fields for Blurry Monocular Video

Minh-Quan Viet Bui*, Jongmin Park*, Juan Luis Gonzalez Bello, Jaeho Moon, Jihyong Oh, Munchurl Kim

IEEE Transactions on Pattern Analysis and Machine Intelligence

Journal

ProNeRF: Learning Efficient Projection-Aware Ray Sampling for Fine-Grained Implicit Neural Radiance Fields

Juan Luis Gonzalez Bello*, Minh-Quan Viet Bui*, Munchurl Kim

IEEE Access

Journal

Transfer multi-source knowledge via scale-aware online domain adaptation in depth estimation for autonomous driving

Phan Thi Huyen Thanh*, Minh-Quan Viet Bui*, Duc Dung Nguyen, Tran Vu Pham, Truong Vinh Truong Duy, Natori Naotake

Image and Vision Computing

Journal

eGAC3D: enhancing depth adaptive convolution and depth estimation for monocular 3D object pose detection

Duc Tuan Ngo*, Minh-Quan Viet Bui*, Duc Dung Nguyen, Hoang-Anh Pham

PeerJ Computer Science

Journal

GAC3D: improving monocular 3D object detection with ground-guide model and adaptive convolution

Minh-Quan Viet Bui*, Duc Tuan Ngo*, Hoang-Anh Pham, Duc Dung Nguyen

PeerJ Computer Science

Get In Touch

Email

bvmquan@kaist.ac.kr

Laboratory

N24 Building
Room 1106
KAIST