Kang Du

Kang Du 杜康

Graphics Researcher & Simulation Systems Builder

PhD candidate, HKUST (Guangzhou)

Experience

  • 2025–Jun 2026 Simulation Platform Lead, LingBot 蚂蚁灵波
  • 2024–Present PhD Candidate, HKUST (Guangzhou)
  • 2023–2024 MBA, The University of Hong Kong
  • 2022–2024 3D Simulation & Rendering Expert, Tencent
  • 2021–2022 Real-time Rendering Engine Lead, Meituan
  • 2020–2021 Graphics Rendering Expert, ByteDance
  • 2016–2020 Founder, 云深间造 (VR startup)
  • 2014 BSc, Texas A&M University
01

Short Bio

I am a PhD candidate at HKUST (Guangzhou), advised by Prof. Zeyu Wang and co-advised by Prof. Ruizhen Hu. My research is on inverse rendering, neural rendering, and 3D Gaussian Splatting, with a focus on light-aware and editable world models — turning real-world captures into scenes that can be decomposed, edited, relit, and re-simulated for robotics and embodied AI.

Before returning to academia, I spent nearly ten years building 3D systems in industry. Most recently I led the simulation platform at LingBot (2025–2026), where I built the data simulation team from the ground up. Earlier I worked on device–cloud collaborative rendering at Tencent (2022–2024), real-time rendering engines at Meituan (2021–2022), and graphics rendering at ByteDance (2020–2021). Before that I founded 云深间造 (2016–2020), a VR startup for virtual property viewing, which received the Technology Innovation Award at the 4th China Home Furnishings Innovation Summit.

I obtained my MBA from the University of Hong Kong in 2024, and my bachelor’s degree from Texas A&M University in 2014.

Research areas: Computer Graphics · Inverse Rendering · Editable World Models · Simulation for Robotics & Embodied AI

02

Selected Work

MVID: Feed-Forward Multi-View Intrinsic Image Decomposition

SIGGRAPH Asia 2026 · In collaboration with Tencent

Kang Du and collaborators

Feed-forward decomposition of multi-view images into consistent albedo, shading, and specular residual — no per-scene optimization.

UAVLight

UAVLight: A Benchmark for Illumination-Robust 3D Reconstruction in Unmanned Aerial Vehicle (UAV) Scenes

CVPR 2026 · In collaboration with Meituan

Kang Du, Xue Liao, Junpeng Xia, Chaozheng Guo, Yi Gu, Yirui Guan, Duotun Wang, Sheng Huang, Zeyu Wang

A benchmark for illumination-robust reconstruction in real UAV scenes: large-scale outdoor captures across multiple time slots under changing sunlight and shadows.

InstGS

InstGS: Shared-Template Gaussian Instancing for Object-Redundancy-Free Rendering

ECCV 2026

Zi'ang Lu, Zhang Qian, Kang Du, Dong Liang, John Li, Xinyao Wei, Zeyu Wang, Jinyuan Jia

Shared-template Gaussian instancing that removes object redundancy, enabling compact and efficient rendering of repeated content.

Editable Real-World Simulation System

Editable Real-World Simulation System

2026 · At LingBot 蚂蚁灵波

Role: Simulation platform lead — built the data simulation team from the ground up and established the simulation platform.

Connects real-environment capture, reconstruction, scene editing, and simulation data production for robot data augmentation and teleoperation collection.

GS-ID: Illumination Decomposition on Gaussian Splatting via Adaptive Light Aggregation and Diffusion-Guided Material Priors

ICCV 2025 · In collaboration with Tencent AI Lab

Kang Du, Zhihao Liang, Yulin Shen, Zeyu Wang

Inverse rendering on 3D Gaussian Splatting: recovers geometry, material, and lighting from multi-view images for material editing and relighting.

Device–Cloud Collaborative Rendering System

Device–Cloud Collaborative Rendering System

2022–2024 · At Tencent

Role: 3D simulation & rendering expert

Splits rendering between device and cloud for cloud rendering and cloud gaming: real-time rendering, low-latency streaming, and compute scheduling in production.

Web 3D Editor & Content Tools

Web 3D Editor & Content Tools

2021–2022 · At Meituan

Role: Real-time rendering engine lead

Browser-based 3D editors letting non-expert teams build, edit, and publish 3D scenes — web real-time rendering, editor architecture, and asset pipelines.

Playable Ads Rendering Engine

2020–2021 · At ByteDance

Role: Graphics rendering expert

A real-time rendering engine for playable ads — interactive HTML5 creatives that run inside the feed. Every scene ships as a self-contained bundle of a few megabytes with no external requests, so the engine had to fit rendering, animation, and interaction into a very tight size and performance budget across a wide range of phones.

Virtual Property Viewing VR System

2016–2020 · Founder at 云深间造 (startup)

Role: Founder

A commercial VR product for virtual property viewing: real-time 3D spaces and interactive walkthroughs — the starting point of my path toward editable world models.

Award: Technology Innovation Award (company) and Innovation Elite Award (founder), 4th China Home Furnishings Innovation Summit, 2019 [coverage]

03

Contact

Feel free to reach out if you are interested in inverse rendering, editable world models, simulation for robotics, or related collaboration.

kdu800@connect.hkust-gz.edu.cn
270382069@qq.com

Email · Google Scholar · GitHub · LinkedIn · CV