Enhanced Event-Based Video Reconstruction with Motion Compensation

arXiv:2403.11961v1 Announce Type: cross
Abstract: Deep neural networks for event-based video reconstruction often suffer from a lack of interpretability and have high memory demands. A lightweight network called CISTA-LSTC has recently been introduced showing that high-quality reconstruction can be achieved through the systematic design of its architecture. However, its modelling assumption that input signals and output reconstructed frame share the same sparse representation neglects the displacement caused by motion. To address this, we propose warping the input intensity frames and …

abstract architecture arxiv compensation cs.ai cs.cv cs.lg design event however interpretability memory modelling network networks neural networks quality through type video