UvA-DARE (Digital Academic Repository) On the benefit of adversarial training for monocular depth estimation
Rick W. Groenendijk, Sezer Karaoglu, T. Gevers et al.
· 0 citations
We have 2 of 10 papers
We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.
Not the right person? Other researchers publish under this name.
Computer Vision and Image Understanding
It is concluded that adversarial training is beneficial if and only if the reconstruction loss is not too constrained, and non-adversarial training outperforms (or is on par with) any method trained with a GAN when a constrained reconstruction loss is used in combination with batch normalisation.
R. Groenendijk, Sezer Karaoglu, Theo Gevers et al.
· 0 citations