Search Results for author: A. Murat Tekalp

Found 22 papers, 6 papers with code

PAON: A New Neuron Model using Padé Approximants

no code implementations18 Mar 2024 Onur Keleş, A. Murat Tekalp

In this paper, we introduce a brand new neuron model called Pade neurons (Paons), inspired by the Pade approximants, which is the best mathematical approximation of a transcendental function as a ratio of polynomials with different orders.

Image Super-Resolution

Training Generative Image Super-Resolution Models by Wavelet-Domain Losses Enables Better Control of Artifacts

1 code implementation29 Feb 2024 Cansu Korkmaz, A. Murat Tekalp, Zafer Dogan

Although some recent works focused on the differentiation of details and artifacts, this is a very challenging problem and a satisfactory solution is yet to be found.

Image Super-Resolution

Saliency-aware End-to-end Learned Variable-Bitrate 360-degree Image Compression

no code implementations14 Feb 2024 Oguzhan Gungordu, A. Murat Tekalp

Effective compression of 360$^\circ$ images, also referred to as omnidirectional images (ODIs), is of high interest for various virtual reality (VR) and related applications.

Image Compression

Motion-Adaptive Inference for Flexible Learned B-Frame Compression

no code implementations13 Feb 2024 M. Akin Yilmaz, O. Ugur Ulas, Ahmet Bilican, A. Murat Tekalp

As a remedy, we propose controlling the motion range for flow prediction during inference (to approximately match the range of motions in the training data) by downsampling video frames adaptively according to amount of motion and level of hierarchy in order to compress all B-frames using a single flexible-rate model.

Video Compression

Trustworthy SR: Resolving Ambiguity in Image Super-resolution via Diffusion Models and Human Feedback

no code implementations12 Feb 2024 Cansu Korkmaz, Ege Cirakman, A. Murat Tekalp, Zafer Dogan

This strategy leverages the high-quality image generation capabilities of DMs, while recognizing the importance of obtaining a single trustworthy solution, especially in use cases, such as identification of specific digits or letters, where generating multiple feasible solutions may not lead to a reliable outcome.

Image Generation Image Super-Resolution

Multi-Scale Deformable Alignment and Content-Adaptive Inference for Flexible-Rate Bi-Directional Video Compression

1 code implementation28 Jun 2023 M. Akin Yilmaz, O. Ugur Ulas, A. Murat Tekalp

The lack of ability to adapt the motion compensation model to video content is an important limitation of current end-to-end learned video compression models.

Motion Compensation Video Compression

Multi-Field De-interlacing using Deformable Convolution Residual Blocks and Self-Attention

no code implementations21 Sep 2022 Ronglei Ji, A. Murat Tekalp

Although deep learning has made significant impact on image/video restoration and super-resolution, learned deinterlacing has so far received less attention in academia or industry.

Super-Resolution Video Deinterlacing +1

MMSR: Multiple-Model Learned Image Super-Resolution Benefiting From Class-Specific Image Priors

no code implementations18 Sep 2022 Cansu Korkmaz, A. Murat Tekalp, Zafer Dogan

As a result, the performance of an SR model varies noticeably from image to image over a test set depending on whether characteristics of specific images are similar to those in the training set or not.

Image Super-Resolution

Perception-Distortion Trade-off in the SR Space Spanned by Flow Models

no code implementations18 Sep 2022 Cansu Korkmaz, A. Murat Tekalp, Zafer Dogan, Erkut Erdem, Aykut Erdem

We achieve this by benefiting from a diverse set of feasible photo-realistic solutions in the SR space spanned by flow models.

Super-Resolution

Flexible-Rate Learned Hierarchical Bi-Directional Video Compression With Motion Refinement and Frame-Level Bit Allocation

2 code implementations27 Jun 2022 Eren Cetin, M. Akin Yilmaz, A. Murat Tekalp

This paper presents improvements and novel additions to our recent work on end-to-end optimized hierarchical bi-directional video compression to further advance the state-of-the-art in learned video compression.

Image Compression Motion Estimation +1

End-to-End Rate-Distortion Optimized Learned Hierarchical Bi-Directional Video Compression

2 code implementations17 Dec 2021 M. Akin Yilmaz, A. Murat Tekalp

Conventional video compression (VC) methods are based on motion compensated transform coding, and the steps of motion estimation, mode and quantization parameter selection, and entropy coding are optimized individually due to the combinatorial nature of the end-to-end optimization problem.

Motion Estimation MS-SSIM +3

Two-stage domain adapted training for better generalization in real-world image restoration and super-resolution

no code implementations1 Jun 2021 Cansu Korkmaz, A. Murat Tekalp, Zafer Dogan

It is well-known that in inverse problems, end-to-end trained networks overfit the degradation model seen in the training set, i. e., they do not generalize to other types of degradations well.

Image Restoration Super-Resolution

Self-Organized Residual Blocks for Image Super-Resolution

no code implementations31 May 2021 Onur Keleş, A. Murat Tekalp, Junaid Malik, Serkan Kiranyaz

It has become a standard practice to use the convolutional networks (ConvNet) with RELU non-linearity in image restoration and super-resolution (SR).

Image Restoration Image Super-Resolution

DFPN: Deformable Frame Prediction Network

1 code implementation26 May 2021 M. Akin Yilmaz, A. Murat Tekalp

Learned frame prediction is a current problem of interest in computer vision and video compression.

Video Compression

Self-Organized Variational Autoencoders (Self-VAE) for Learned Image Compression

no code implementations25 May 2021 M. Akin Yilmaz, Onur Keleş, Hilal Güven, A. Murat Tekalp, Junaid Malik, Serkan Kiranyaz

In end-to-end optimized learned image compression, it is standard practice to use a convolutional variational autoencoder with generalized divisive normalization (GDN) to transform images into a latent space.

Image Compression

Editorial: Introduction to the Issue on Deep Learning for Image/Video Restoration and Compression

no code implementations9 Feb 2021 A. Murat Tekalp, Michele Covell, Radu Timofte, Chao Dong

Recent works have shown that learned models can achieve significant performance gains, especially in terms of perceptual quality measures, over traditional methods.

Image Restoration Video Restoration

Effect of Architectures and Training Methods on the Performance of Learned Video Frame Prediction

no code implementations13 Aug 2020 M. Akin Yilmaz, A. Murat Tekalp

We analyze the performance of feedforward vs. recurrent neural network (RNN) architectures and associated training methods for learned frame prediction.

End-to-End Rate-Distortion Optimization for Bi-Directional Learned Video Compression

no code implementations11 Aug 2020 M. Akin Yilmaz, A. Murat Tekalp

Conventional video compression methods employ a linear transform and block motion model, and the steps of motion estimation, mode and quantization parameter selection, and entropy coding are optimized individually due to combinatorial nature of the end-to-end optimization problem.

Motion Estimation Quantization +1

Can Learned Frame-Prediction Compete with Block-Motion Compensation for Video Coding?

no code implementations17 Jul 2020 Serkan Sulun, A. Murat Tekalp

Given recent advances in learned video prediction, we investigate whether a simple video codec using a pre-trained deep model for next frame prediction based on previously encoded/decoded frames without sending any motion side information can compete with standard video codecs based on block-motion compensation.

Motion Compensation Video Prediction

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