In a recent interview on RTHK Radio 1's "Under the Sun" program, Prof. Sai-Kit YEUNG, Professor of the Division of Integrative Systems and Design (ISD), the Department of Computer Science and Engineering (CSE), and the Department of Ocean Science (OCES), shares insights on how his 3D scene understanding research advances coral conservation efforts.

Prof. Yeung has pioneered an advanced underwater scene understanding technology that can generate high-precision 3D models of coral reefs, providing vital data for coral ecology research. Beyond large-scale, efficient, and automated data collection, this solution enables precise measurement of key reef metrics—such as fractal dimension, rugosity, and coral coverage. Additionally, it facilitates long-term monitoring by comparing 3D models over time, offering insights into changes in coral coverage, geometric complexity, and overall ecosystem health.

Prof. Yeung's vision extends to integrating this technology with underwater robots for automated 3D scanning, offering a cost-effective alternative to traditional diver-based surveys, aiming at enhancing the efficiency and consistency of coral reef monitoring. The automation not only reduces human risk but also enables continuous monitoring in conditions that would be challenging for human divers.

He also places high importance on MarineAI for quantifying coral bleaching and predicting potential threats to marine ecosystems. By utilizing AI-powered tools, actionable data can be yielded for government officials and marine biologists to make data-driven decisions for conservation efforts.

Tune in to Prof. Yeung’s interview here:

Part 1: https://www.rthk.hk/radio/radio1/programme/underthesun/episode/1004252

Part 2: https://www.rthk.hk/radio/radio1/programme/underthesun/episode/1005588

Learn more about Prof. Yeung’s projects:

• 3D Mapping and Scene Understanding/Editing:
  • Photo-SLAM: Real-time Simultaneous Localization and Photorealistic Mapping for Monocular, Stereo, and RGB-D Cameras
  • StyleCity: Large-Scale 3D Urban Scenes Stylization
• Marine AI:
  • CoralSCOP: Segment any COral Image on this Planet
  • MarineInst: A Foundation Model for Marine Image Analysis with Instance Visual Description
  • HKCoral: Benchmark for Dense Coral Growth Form Segmentation in the Wild
  • Real-time GAN-based Image Enhancement for Robust Underwater Monocular SLAM

About Prof. Sai-Kit YEUNG:
Prof. Sai-Kit Yeung is an expert in computer vision and computer graphics, with research interests spanning 3D vision and visual understanding, generative AI, computational design and fabrication, and human-AI interaction. Recently, he has collaborated closely with marine biologists to develop innovative AI technologies and integrative systems addressing challenges in marine biodiversity and sustainability. He has published extensively in premier computer vision and graphics venues, with numerous full oral papers presented at CVPR, ICCV, ECCV, and AAAI. His work has received Best Paper Honorable Mention Awards at ICCP 2015 and 3DV 2016.

Prof. Yeung has been actively serving as a senior committee member in major AI, computer vision, computer graphics, and robotics conferences. These include roles as a Senior Program Committee member for IJCAI 2021 and AAAI 2021 and 2022, an Area Chair for ICCV 2023, CVPR 2023, 2024, and 2025, NeurIPS 2024, and ICML 2025, as well as an Associate Editor (Robot Learning) for ICRA 2024 and 2025. He also served as Course Chair for SIGGRAPH Asia 2019 and regularly contributes as a Technical Papers Committee member for Eurographics, SIGGRAPH, and SIGGRAPH Asia. Currently, he is an Associate Editor of the ACM Transactions on Graphics (TOG).