3 accepted papers
Monocular depth priors have been widely adopted by neural rendering in multi-view based tasks such as 3D reconstruction and novel view synthesis. However, due to the inconsistent prediction on each view, how to more effectively leverage monocular cues in a multi-view context remains a challenge. Cur…
Traditional phase retrieval is generally concerned with re-covering a signal from its Fourier magnitude measurements whose inherent ambiguities make this problem especially difficult. In this work, we present an efficient phase retrieval technique from the single fractional Fourier transform (FrFT)…
We address the problem of removing undesirable reflections from a single image captured through a glass surface, which is an ill-posed, challenging but practically important problem for photo enhancement. Inspired by iterative structure reduction for hidden community detection in social networks, we…