Closed JasonWUCHI closed 1 month ago
Thank you interest in our paper :)
\mathcal{f}_{\phi}
$ is the normalizing flow network which transforms a simple distribution $z
$ to . Since the network is invertible $\mathcal{f}_{\phi}^{-1}
$ and we are interested to model the error $\bar{\theta}
$, hence $\bar{\theta} = \mathcal{f}_{\phi}^{-1}(z)
$\mathcal{f}_{\phi}^{-1}(\bar{\theta_{g}})
$ with $(\theta_{g} - \theta)/\sigma
$ and omitted for simplicity.This formulation is adapted from RLE, ICCV 2021 which defined residual log-likelihood. You can refer to the original paper if it helps.
Dear author,
I am trying to understand the equation 4 in the paper, could you help me to clarify some point?
Thank you in advance!