no code implementations • ECCV 2018 • Meng Tang, Federico Perazzi, Abdelaziz Djelouah, Ismail Ben Ayed, Christopher Schroers, Yuri Boykov
This approach simplifies weakly-supervised training by avoiding extra MRF/CRF inference steps or layers explicitly generating full masks, while improving both the quality and efficiency of training.
no code implementations • CVPR 2018 • Simone Meyer, Abdelaziz Djelouah, Brian McWilliams, Alexander Sorkine-Hornung, Markus Gross, Christopher Schroers
We show that this is superior to the hand-crafted heuristics previously used in phase-based methods and also compares favorably to recent deep learning based approaches for video frame interpolation on challenging datasets.
no code implementations • CVPR 2018 • Meng Tang, Abdelaziz Djelouah, Federico Perazzi, Yuri Boykov, Christopher Schroers
Our normalized cut loss approach to segmentation brings the quality of weakly-supervised training significantly closer to fully supervised methods.
no code implementations • 9 Aug 2018 • Simone Meyer, Victor Cornillère, Abdelaziz Djelouah, Christopher Schroers, Markus Gross
Traditional approaches for color propagation in videos rely on some form of matching between consecutive video frames.
no code implementations • 10 Dec 2018 • Leonhard Helminger, Abdelaziz Djelouah, Markus Gross, Romann M. Weber
We present a deep generative model that learns disentangled static and dynamic representations of data from unordered input.
no code implementations • 4 Jun 2019 • Joaquim Campos, Simon Meierhans, Abdelaziz Djelouah, Christopher Schroers
The field of neural image compression has witnessed exciting progress as recently proposed architectures already surpass the established transform coding based approaches.
no code implementations • ICCV 2019 • Abdelaziz Djelouah, Joaquim Campos, Simone Schaub-Meyer, Christopher Schroers
We propose to compute residuals directly in latent space instead of in pixel space as this allows to reuse the same image compression network for both key frames and intermediate frames.
no code implementations • ICLR Workshop Neural_Compression 2021 • Leonhard Helminger, Abdelaziz Djelouah, Markus Gross, Christopher Schroers
However, state-of-the-art solutions for deep image compression typically employ autoencoders which map the input to a lower dimensional latent space and thus irreversibly discard information already before quantization.
no code implementations • 9 Sep 2020 • Leonhard Helminger, Michael Bernasconi, Abdelaziz Djelouah, Markus Gross, Christopher Schroers
In contrast to this, we propose using normalizing flows to model the distribution of the target content and to use this as a prior in a maximum a posteriori (MAP) formulation.
no code implementations • 7 Jan 2022 • Leonhard Helminger, Roberto Azevedo, Abdelaziz Djelouah, Markus Gross, Christopher Schroers
Recently, significant progress has been made in learned image and video compression.
no code implementations • CVPR 2023 • Markus Plack, Karlis Martins Briedis, Abdelaziz Djelouah, Matthias B. Hullin, Markus Gross, Christopher Schroers
Through this error estimation, our method can produce even higher-quality intermediate frames using only a fraction of the time compared to a full rendering.
no code implementations • CVPR 2023 • Michael Bernasconi, Abdelaziz Djelouah, Farnood Salehi, Markus Gross, Christopher Schroers
This renders our model applicable for different types of data not seen during the training such as normals.