Researcher:
Yılmaz, Melih

Profile Picture
ORCID

Job Title

Undergraduate Student

First Name

Melih

Last Name

Yılmaz

Name

Name Variants

Yılmaz, Melih

Email Address

Birth Date

Filters

20203

Advanced Search

Filter by

Settings

Researcher Of Publications: search.filters.isAuthorOfPublication.ddbb5e97-9ccb-4403-92b4-9068749e51ee

Search Results

Now showing 1 - 3 of 3
  • Placeholder
    PublicationMetadata only
    New results in end-to-end image and video compression by deep learning
    (IEEE, 2020) N/A; Department of Electrical and Electronics Engineering; Department of Electrical and Electronics Engineering; N/A; Department of Electrical and Electronics Engineering; Özsoy, Gökberk; Yılmaz, Melih; Kırmemiş, Ogün; Tekalp, Ahmet Murat; Undergraduate Student; Undergraduate Student; PhD Student; Faculty Member; Department of Electrical and Electronics Engineering; College of Engineering; College of Engineering; Graduate School of Sciences and Engineering; College of Engineering; N/A; N/A; N/A; 26207
    Expanding ubiquity of high-resolution digital video over the internet calls for better compression methods to enable streaming with higher compression efficiency and lower latency. Recently, important gains have been achieved in learned image compression by using end-to-end learned models. However, these improvements haven't been fully leveraged in video compression. This paper aims to improve upon work proposed by Lu et al. in CVPR 2019, which has been claimed to outperform conventional video codecs in terms of PSNR and provide some implementation details that are absent in the original paper. Ultimately, we show that modeling latent symbols by Laplacian distribution outperforms the Gaussian assumption used in the original work and also demonstrate in a repeatable fashion that our learned model is superior to x264 video codec in terms of PSNR over a range of compression rates measured by bit-per-pixel.
  • Placeholder
    PublicationMetadata only
    New results in end-to-end image and video compression by deep learning
    (Institute of Electrical and Electronics Engineers Inc., 2020) Department of Electrical and Electronics Engineering; N/A; Department of Electrical and Electronics Engineering; Department of Electrical and Electronics Engineering; Tekalp, Ahmet Murat; Kırmemiş, Ogün; Özsoy, Gökberk; Yılmaz, Melih; Faculty Member; PhD Student; Student; Student; Department of Electrical and Electronics Engineering; College of Engineering; Graduate School of Sciences and Engineering; College of Engineering; College of Engineering; 26207; N/A; N/A; N/A
    Expanding ubiquity of high-resolution digital video over the Internet calls for better compression methods to enable streaming with higher compression efficiency and lower latency. Recently, important gains have been achieved in learned image compression by using end-to-end learned models. However, these improvements haven't been fully leveraged in video compression. This paper aims to improve upon work proposed by Lu et al. in CVPR 2019, which has been claimed to outperform conventional video codecs in terms of PSNR and provide some implementation details that are absent in the original paper. Ultimately, we show that modeling latent symbols by Laplacian distribution outperforms the Gaussian assumption used in the original work and also demonstrate in a repeatable fashion that our learned model is superior to x264 video codec in terms of PSNR over a range of compression rates measured by bit-per-pixel.
  • Thumbnail Image
    PublicationOpen Access
    End-to-end rate-distortion optimization for bi-directional learned video compression
    (Institute of Electrical and Electronics Engineers (IEEE), 2020) Department of Electrical and Electronics Engineering; Yılmaz, Melih; Tekalp, Ahmet Murat; Faculty Member; Department of Electrical and Electronics Engineering; College of Engineering; N/A; 26207
    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. Learned video compression allows end-to-end rate-distortion optimized training of all nonlinear modules, quantization parameter and entropy model simultaneously. While previous work on learned video compression considered training a sequential video codec based on end-to-end optimization of cost averaged over pairs of successive frames, it is well-known in conventional video compression that hierarchical, bi-directional coding outperforms sequential compression. In this paper, we propose for the first time end-to-end optimization of a hierarchical, bi-directional motion compensated learned codec by accumulating cost function over fixed-size groups of pictures (GOP). Experimental results show that the rate-distortion performance of our proposed learned bi-directional GOP coder outperforms the state-of-the-art end-to-end optimized learned sequential compression as expected.