Daniel Rho

PhD student, computer science, UNC Chapel Hill

I am a PhD student in computer science at UNC Chapel Hill, advised by Prof. Roni Sengupta. Before UNC, I worked as a research engineer at KT AI Tech Lab, and completed my MS at Sungkyunkwan University with Prof. Jong Hwan Ko and Prof. Eunbyung Park.

My research focuses on recovering 3D and 4D scenes from real world observations — their geometry, motion, and the physics that drives them.

Publications

  1. ProJo4D: Progressive joint optimization for sparse-view inverse physics estimation

    Daniel Rho, Jun Myeong Choi, Biswadip Dey, Roni Sengupta

    TMLR 2026 project paper

  2. NFL-BA: Improving endoscopic SLAM with near-field light bundle adjustment

    Andrea Dunn Beltran*, Daniel Rho*, Marc Niethammer, Roni Sengupta

    NeurIPS 2025 project paper

  3. F-3DGS: Factorized coordinates and representations for 3D Gaussian splatting

    Xiangyu Sun, Joo Chan Lee, Daniel Rho, Jong Hwan Ko, Usman Ali, Eunbyung Park

    ACM MM 2024 paper

  4. Compact 3D Gaussian representation for radiance field

    Joo Chan Lee, Daniel Rho, Xiangyu Sun, Jong Hwan Ko, Eunbyung Park

    CVPR 2024, highlight project paper code

  5. Coordinate-aware modulation for neural fields

    Joo Chan Lee, Daniel Rho, Seungtae Nam, Jong Hwan Ko, Eunbyung Park

    ICLR 2024, spotlight project

  6. Mip-Grid: Anti-aliased grid representations for neural radiance fields

    Seungtae Nam, Daniel Rho, Jong Hwan Ko, Eunbyung Park

    NeurIPS 2023 paper

  7. FFNeRV: Flow-guided frame-wise neural representations for videos

    Joo Chan Lee, Daniel Rho, Jong Hwan Ko†, Eunbyung Park†

    ACM MM 2023 project paper code

  8. Masked wavelet representation for compact neural radiance fields

    Daniel Rho*, Byeonghyeon Lee*, Seungtae Nam, Joo Chan Lee, Jong Hwan Ko†, Eunbyung Park†

    CVPR 2023 project paper code

  9. Regression to classification: Waveform encoding for neural field-based audio signal representation

    TaeSoo Kim*, Daniel Rho*, Gahui Lee, JaeHan Park, Jong Hwan Ko

    ICASSP 2023 paper

  10. Neural residual flow fields for efficient video representations

    Daniel Rho, Junwoo Cho, Jong Hwan Ko, Eunbyung Park

    ACCV 2022 paper code

  11. Streamable neural fields

    Junwoo Cho*, Seungtae Nam*, Daniel Rho, Jong Hwan Ko, Eunbyung Park

    ECCV 2022 paper code

  12. NAS-VAD: Neural architecture search for voice activity detection

    Daniel Rho, Jinhyeok Park, Jong Hwan Ko

    Interspeech 2022 paper code

Preprints

  1. Stop holding your breath: CT-informed Gaussian splatting for dynamic bronchoscopy

    Andrea Dunn Beltran, Daniel Rho, Aarav Mehta, Xinqi Xiong, Raúl San José Estépar, Ron Alterovitz, Marc Niethammer, Roni Sengupta

    arXiv 2026 project paper

  2. Understanding contrastive learning through the lens of margins

    Daniel Rho, TaeSoo Kim, Sooill Park, Jaehyun Park, JaeHan Park

    arXiv 2023 paper

Experience

2024 to present

PhD, Computer Science

UNC Chapel Hill, advisor: Roni Sengupta

May to Jul 2025

Research Intern

Lenovo Research

Aug 2022 to Jun 2024

Research Engineer

AI Tech Lab, KT

2020 to 2022

MS, Artificial Intelligence

Sungkyunkwan University, advisors: Jong Hwan Ko, Eunbyung Park

2014 to 2020

BS, Economics and Computer Science

Sungkyunkwan University