28 citations · 72 across the 5 of their papers we have counts for
6 papers
Jointformer: Single-Frame Lifting Transformer with Error Prediction and Refinement for 3D Human Pose Estimation
Sebastian Lutz, Richard Blythman, Koustav Ghosal +3
Monocular 3D human pose estimation technologies have the potential to greatly increase the availability of human movement data. The best-performing models for single-image 2D-3D li…
Frequency Domain Loss Function for Deep Exposure Correction of Dark Images
Ojasvi Yadav, Koustav Ghosal, Sebastian Lutz +1
We address the problem of exposure correction of dark, blurry and noisy images captured in low-light conditions in the wild. Classical image-denoising filters work well in the freq…
Foreground color prediction through inverse compositing
Sebastian Lutz, Aljosa Smolic
In natural image matting, the goal is to estimate the opacity of the foreground object in the image. This opacity controls the way the foreground and background is blended in trans…
STaDA: Style Transfer as Data Augmentation
Xu Zheng, Tejo Chalasani, Koustav Ghosal +2
The success of training deep Convolutional Neural Networks (CNNs) heavily depends on a significant amount of labelled data. Recent research has found that neural style transfer alg…
AlphaGAN: Generative adversarial networks for natural image matting
Sebastian Lutz, Konstantinos Amplianitis, Aljosa Smolic
We present the first generative adversarial network (GAN) for natural image matting. Our novel generator network is trained to predict visually appealing alphas with the addition o…
SalNet360: Saliency Maps for omni-directional images with CNN
Rafael Monroy, Sebastian Lutz, Tejo Chalasani +1
The prediction of Visual Attention data from any kind of media is of valuable use to content creators and used to efficiently drive encoding algorithms. With the current trend in t…