tu-darmstadt-informatik/bsc-thesis
1
0
Fork 0
mirror of https://github.com/tu-darmstadt-informatik/bsc-thesis.git synced 2026-01-20 20:11:16 +00:00
Code Issues Packages Projects Releases Wiki Activity

Update conclusion.tex

Browse Source
This commit is contained in:
Simon Meister 2017-11-06 14:06:18 +01:00 committed by GitHub
parent 90bafdbd84
commit fc9ccb5f77
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
1 changed files with 8 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

8
conclusion.tex
View File

@ -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.