Search Results for author: Abdelaziz Djelouah

Found 9 papers, 0 papers with code

Blind Image Restoration with Flow Based Priors

no code implementations9 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.

Denoising Image Enhancement +1

Lossy Image Compression with Normalizing Flows

no code implementations24 Aug 2020 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.

Image Compression Quantization

Neural Inter-Frame Compression for Video Coding

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.

Image Compression Motion Compensation +1

Content Adaptive Optimization for Neural Image Compression

no code implementations4 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.

Image Compression

Disentangled Dynamic Representations from Unordered Data

no code implementations10 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.

Deep Video Color Propagation

no code implementations9 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.

Style Transfer

Normalized Cut Loss for Weakly-supervised CNN Segmentation

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.

Interactive Segmentation Semantic Segmentation

PhaseNet for Video Frame Interpolation

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.

Video Frame Interpolation

On Regularized Losses for Weakly-supervised CNN Segmentation

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.

Semantic Segmentation

Cannot find the paper you are looking for? You can Submit a new open access paper.