RGBD indoor semantic segmentation with segmentation transformer

• Main Author: Choong, Han Yi
• Other Authors: Sinno Jialin Pan
• Format: Final Year Project
• Language: English
• Published: Nanyang Technological University 2022
• Subjects: Engineering::Computer science and engineering::Computing methodologies::Image processing and computer vision
• Online Access: https://hdl.handle.net/10356/156004
• Institution: Nanyang Technological University

Depth information has proven to be a useful cue in the semantic segmentation of RGB-D images for providing a geometric counterpart to the RGB representation. Modern approaches typically formulate semantic segmentation as a per-pixel classification task, while instance-level segmentation uses an alternative mask classification. Recent insight is that mask classification is sufficiently general to solve both semantic- and instance-level segmentation tasks in a unified manner using the exact same model, loss, and training procedure. Following this observation, this project aims to study segmentation transformers under RGBD setting with a simple mask classification model which predicts a set of binary masks, each associated with a single global class label prediction.