3D Object Detection in Context
This work presents a second contribution attempting to push the performance of the contemporary state-of-the-art 3D object detector, RBGNet, by introducing self-attention on multiple levels. Inspired by self-attention is introduced at; (1) the point patch level to capture correlations between parts, or geometries, of objects, (2) the object candidate level to capture relationships between objects in the scene, and (3) the scene level to capture contextual cues. Through a series of experiments, the introduced self-attention modules prove to have a positive effect on the performance of the RBGNet baseline.
S.M.J. Abu Ghazal, "3D Object Detection in Context", M.S. Thesis, Computer Vision, MBZUAI, Abu Dhabi, UAE, 2022.