From fc9ccb5f770643a36e227177e757e3b6fac8beca Mon Sep 17 00:00:00 2001 From: Simon Meister Date: Mon, 6 Nov 2017 14:06:18 +0100 Subject: [PATCH] Update conclusion.tex --- conclusion.tex | 8 ++++++++ 1 file changed, 8 insertions(+) diff --git a/conclusion.tex b/conclusion.tex index 72076a7..6ca2ee9 100644 --- a/conclusion.tex +++ b/conclusion.tex @@ -28,3 +28,11 @@ On Cityscapes, we could continue train the instance segmentation components to improve detection and masks and avoid forgetting instance segmentation. As an alternative to this training scheme, we could investigate training on a pure instance segmentation dataset with unsupervised warping-based proxy losses for the motion (and depth) prediction. + +\paragraph{Temporal consistency} +A next step after the two aforementioned ones could be to extend our network to exploit more than two +temporally consecutive frames, which has previously been shown to be beneficial in the +context of scene flow \cite{TemporalSF}. +In fact, by incorporating recurrent neural networks, e.g. LSTMs \cite{LSTM}, +into our architecture, we could enable temporally consistent motion estimation +from image sequences of arbitrary length.