tu-darmstadt-informatik/bsc-thesis
1
0
Fork 0
mirror of https://github.com/tu-darmstadt-informatik/bsc-thesis.git synced 2025-12-13 09:55:49 +00:00
Code Issues Packages Projects Releases Wiki Activity

edit abstract

Browse Source
This commit is contained in:
Simon Meister 2017-10-13 14:56:58 +02:00
parent 146dd61ed2
commit 1b80c15568
1 changed files with 6 additions and 5 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

11
abstract.tex
View File

@ -1,10 +1,10 @@
\begin{abstract} \begin{abstract}
Many state of the art energy-minimization approaches to optical flow and scene flow estimation Many state of the art energy-minimization approaches to optical flow and scene flow estimation
rely on a rigid scene model, where the scene is represented as an ensemble of distinct, rely on a (piecewise) rigid scene model, where the scene is represented as an ensemble of distinct,
rigidly moving objects, a static background and a moving camera. rigidly moving components, a static background and a moving camera.
By using a physical scene model, the search space of the optimization problem is significantly By constraining the optimization problem with a physically sound scene model,
reduced, enabling higly accurate motion estimation. these approaches enable higly accurate motion estimation.
With the advent of deep learning methods, it has become popular to re-purpose generic deep networks With the advent of deep learning methods, it has become popular to re-purpose generic deep networks
for classical computer vision problems involving pixel-wise estimation. for classical computer vision problems involving pixel-wise estimation.
@ -17,7 +17,8 @@ and any physical constraints within the scene.
We introduce an end-to-end deep learning approach for dense motion estimation We introduce an end-to-end deep learning approach for dense motion estimation
that respects the structure of the scene as being composed of distinct objects, that respects the structure of the scene as being composed of distinct objects,
thus unifying end-to-end deep networks and a strong physical scene model. thus combining the representation learning benefits of end-to-end deep networks
with a physically plausible scene model.
Building on recent advanced in region-based convolutional networks (R-CNNs), we integrate motion Building on recent advanced in region-based convolutional networks (R-CNNs), we integrate motion
estimation with instance segmentation. estimation with instance segmentation.