More about HKUST
Multi-modal Data Fusion and Sensing for Complex Indoor Scenes
The Hong Kong University of Science and Technology Department of Computer Science and Engineering PhD Thesis Defence Title: "Multi-modal Data Fusion and Sensing for Complex Indoor Scenes" By Miss Rongrong GAO Abstract: In is important to promot the vision capabilities for robotics perception, while camera-only-based approach cannot sufficiently capture the (three-dimensional) spatial and contextual nuances essential for effective interaction in diverse environments. This discrepancy emphasizes the need for multi-modal representations to enrich the robots' understanding of their surroundings. Incorporating additional sensing modalities, such as depth, laser radar, and time-of-flight imaging, provides a more holistic and nuanced perception of the physical environment. To this end, this dissertation delves into a comprehensive exploration of multi-modal perception within robotic scenarios. Specifically, this thesis conducts a systematic study on below three pivotal topics: o Geometric learning of time-of-flight data including depth and normal estimation; o Colorization of three-dimensional point cloud data for better scene understanding; o Multi-modal data compression and decompression for better online storage and sharing. This thesis embarks on a series of groundbreaking scientific research for these three topics. The research endeavors to contribute systematic review, state-of-the-art models, innovative methods, and curated data sets to related sub-fields, thereby propelling a step towards enhancing intelligent robot perception. Date: Thursday, 18 July 2024 Time: 3:00pm - 5:00pm Venue: Room 3494 Lifts 25/26 Chairman: Prof. Jidong ZHAO (CIVL) Committee Members: Dr. Qifeng CHEN (Supervisor) Dr. Long CHEN Dr. Yangqiu SONG Prof. Ping TAN (ECE) Dr. Ping LUO (HKU)