0
0

Delete article

Deleted articles cannot be recovered.

Draft of this article would be also deleted.

Are you sure you want to delete this article?

More than 3 years have passed since last update.

【Stereo Depth】SegStereo : Semantic Segmentaionもwarpしてlossを計算

Posted at

SegStereo: Exploiting Semantic Information for Disparity Estimation

![image.png](https://qiita-image-store.s3.ap-northeast-1.amazonaws.com/0/482094/ad95269d-b0c4-c66b-90d6-66c8b3a3e29d.png)

今までSemantic SegmentationをDepthの推定に使う事でEdge周辺のDisparityの推定精度をあげる事などが行われてきた。

この論文では右のSemantic Segmentationの推定の結果をDisparityを用いることで左のSemantic Segmentationにwarpする。左のSemantic SegmentationのGround Truthと比較する事でLsegを計算する事が出来る。

この手法のメリットはDisparityのErrorを色の違い(Photometric Loss)以外にもClassの違いを計算出来る事で多様化している事。

結論

・DisparityにSemantic Segmentaionを使う場合には試してみたい

参考文献

SegStereo: Exploiting Semantic Information for Disparity Estimation https://arxiv.org/pdf/1807.11699.pdf
0
0
0

Register as a new user and use Qiita more conveniently

  1. You get articles that match your needs
  2. You can efficiently read back useful information
  3. You can use dark theme
What you can do with signing up
0
0

Delete article

Deleted articles cannot be recovered.

Draft of this article would be also deleted.

Are you sure you want to delete this article?