no code implementations • 13 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.
1 code implementation • 28 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.
2 code implementations • 27 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.
2 code implementations • 17 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.
1 code implementation • 26 May 2021 • M. Akin Yilmaz, A. Murat Tekalp
Learned frame prediction is a current problem of interest in computer vision and video compression.
no code implementations • 25 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.
no code implementations • 30 Apr 2021 • Onur Keleş, M. Akin Yilmaz, A. Murat Tekalp, Cansu Korkmaz, Zafer Dogan
Others compute a single PSNR from the arithmetic mean of frame MSEs for each video.
no code implementations • 13 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.
no code implementations • 11 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.