Derong Jin 金德容

I am a Ph.D. student in Computer Science at the University of Maryland, College Park, advised by Prof. Ruohan Gao. I also work closely with Prof. Ming C. Lin.

My research lies at the intersection of multimodal learning, generative modeling, and 3D vision. My current work focuses on reconstructing and generating audio-visual environments from minimal observations.

Previously, I earned my B.Eng. at CUHK-Shenzhen in 2024, advised by Prof. Xiaoguang Han.

I am seeking research internship opportunities for Summer 2027.

Featured Research

All publications

A single image becomes a 3D scene with spatially grounded sounds and novel viewpoints.

CVPR 2026

SonoWorld

Turning a single image into an explorable 3D scene with spatial audio grounded in scene semantics and geometry.

Interactive Demo Project page

Multi-view observations and material-aware sound reflections reconstruct room acoustics.

ICCV 2025 Oral Presentation

AV-DAR

Learning room acoustics from sparse measurements with multi-view visual priors and differentiable acoustic beam tracing.

Interactive Demo Project page

For the full spatial-audio experience, explore the demos on a desktop with headphones.

Publications

* Equal contribution

Objects as Audio-Visual Modal Sound Fields

Zisen Shao*, Zihao Wei*, Derong Jin, Ruohan Gao

ECCV 2026

Project Paper arXiv

SonoWorld: From One Image to a 3D Audio-Visual Scene

Derong Jin*, Xiyi Chen*, Ming C. Lin, Ruohan Gao

CVPR 2026

Project Paper arXiv Code Poster

Differentiable Room Acoustic Rendering with Multi-View Vision Priors

Derong Jin, Ruohan Gao

ICCV 2025 · Oral Presentation

Project Paper arXiv Code Video

HMNeRFBench: A Comprehensive Benchmark for Neural Human Radiance Fields

Kenkun Liu, Derong Jin, Ailing Zeng, Xiaoguang Han, Lei Zhang

NeurIPS 2023 · Dataset and Benchmark Track

Project Paper Code

Get3DHuman: Lifting StyleGAN-Human into a 3D Generative Model using Pixel-aligned Reconstruction Priors

Zhangyang Xiong, Di Kang, Derong Jin, Weikai Chen, Linchao Bao, Shuguang Cui, Xiaoguang Han

ICCV 2023

Project Paper arXiv Code

Selected Awards

Outstanding Graduate Award from The Chinese University of Hong Kong, Shenzhen (Top 1.1%)2024
ICPC Asia Regional Silver Medals (Kunming, Shanghai)2021, 2022

Teaching

CMSC498K: Introduction to Multimodal Deep LearningGraduate TA · University of MarylandFall 2025
Algorithms, Data Structures, Programming & ProbabilityUndergraduate TA · CUHK-Shenzhen2022–2024

Academic Service

Peer reviewer: ICLR 2027, AAAI 2026, CVPR 2026, NeurIPS 2026 (Top Reviewer); IEEE Transactions on Emerging Topics in Computing.