1 code implementation • 23 Aug 2021 • Rafia Rahim, Faranak Shamsafar, Andreas Zell
In this work first, we show that these 3D convolutions in stereo networks consume up to 94% of overall network operations and act as a major bottleneck.
3 code implementations • 22 Aug 2021 • Faranak Shamsafar, Samuel Woerz, Rafia Rahim, Andreas Zell
Depending on the dimension of cost volume, we design a 2D and a 3D model with encoder-decoders built from 2D and 3D convolutions, respectively.
Ranked #1 on Stereo Depth Estimation on sceneflow
1 code implementation • 21 Aug 2018 • Muneeb Aadil, Rafia Rahim, Sibt Ul Hussain
Recently, Convolutional Neural Networks (CNNs) have shown promising performance in super-resolution (SR).
4 code implementations • 20 Nov 2017 • Atique ur Rehman, Rafia Rahim, M Shahroz Nadeem, Sibt Ul Hussain
All the existing image steganography methods use manually crafted features to hide binary payloads into cover images.