We propose MorpheuS, a dynamic scene reconstruction method that leverages neural implicit representations
and diffusion priors for achieving 360° reconstruction of a moving object from a monocular RGB-D video.
We present a neural RGB-D SLAM system, Co-SLAM, which performs robust camera
tracking and high-fidelity surface reconstruction in real time. This paper extends
the work presented in my MSc thesis.
We present a refinement framework to boost the performance of pre-trained semi-supervised video object segmentation (VOS) models based on scale inconsistency. Our work consists of a multi-scale attention module with the corresponding self-supervised online adaptation strategy.
We use a MobileNet as a backbone model to estimate the phyiscal physical properties of house-hold containers and their fillings. A data augmentation strategy with consistency measurement is proposed to improve the generalization ability of our model.