Light-Weight EPINET Architecture for Fast Light Field Disparity Estimation

Aktiviteetti: Konferenssiesitelmä


Recent deep learning-based light field disparity estimation algorithms require millions of parameters, which demand high computational cost and limit the model deployment. In this paper, an investigation is carried out to analyze the effect of depthwise separable convolution and ghost modules on state-of-the-art EPINET architecture for disparity estimation. Based on this investigation, four convolutional blocks are proposed to make the EPINET architecture a fast and light-weight network for disparity estimation. The experimental results exhibit that the proposed convolutional blocks have significantly reduced the computational cost of EPINET architecture by up to a factor of 3.89, while achieving comparable disparity maps on HCI Benchmark dataset.
Aikajakso26 syysk. 202228 syysk. 2022
Tapahtuman otsikkoIEEE 24th International Workshop on Multimedia Signal Processing (MMSP)
Tapahtuman tyyppiWorkshop
SijaintiShanghai, KiinaNäytä kartalla
Tunnustuksen arvoInternational

Country of activity

  • Ruotsi