1 code implementation • 19 Apr 2024 • Ronglei Ji, A. Murat Tekalp
We propose a new multi-picture architecture for video deinterlacing or demosaicing by aligning multiple supporting pictures with missing data to a reference picture to be reconstructed, benefiting from both local and global spatio-temporal correlations in the feature space using modified deformable convolution blocks and a novel residual efficient top-$k$ self-attention (kSA) block, respectively.
1 code implementation • 17 Apr 2024 • Cansu Korkmaz, A. Murat Tekalp
This paper presents two contributions: i) We introduce convolutional non-local sparse attention (NLSA) blocks to extend the hybrid transformer architecture in order to further enhance its receptive field.
1 code implementation • 15 Apr 2024 • Zheng Chen, Zongwei Wu, Eduard Zamfir, Kai Zhang, Yulun Zhang, Radu Timofte, Xiaokang Yang, Hongyuan Yu, Cheng Wan, Yuxin Hong, Zhijuan Huang, Yajun Zou, Yuan Huang, Jiamin Lin, Bingnan Han, Xianyu Guan, Yongsheng Yu, Daoan Zhang, Xuanwu Yin, Kunlong Zuo, Jinhua Hao, Kai Zhao, Kun Yuan, Ming Sun, Chao Zhou, Hongyu An, Xinfeng Zhang, Zhiyuan Song, Ziyue Dong, Qing Zhao, Xiaogang Xu, Pengxu Wei, Zhi-chao Dou, Gui-ling Wang, Chih-Chung Hsu, Chia-Ming Lee, Yi-Shiuan Chou, Cansu Korkmaz, A. Murat Tekalp, Yubin Wei, Xiaole Yan, Binren Li, Haonan Chen, Siqi Zhang, Sihan Chen, Amogh Joshi, Nikhil Akalwadi, Sampada Malagi, Palani Yashaswini, Chaitra Desai, Ramesh Ashok Tabib, Ujwala Patil, Uma Mudenagudi, Anjali Sarvaiya, Pooja Choksy, Jagrit Joshi, Shubh Kawa, Kishor Upla, Sushrut Patwardhan, Raghavendra Ramachandra, Sadat Hossain, Geongi Park, S. M. Nadim Uddin, Hao Xu, Yanhui Guo, Aman Urumbekov, Xingzhuo Yan, Wei Hao, Minghan Fu, Isaac Orais, Samuel Smith, Ying Liu, Wangwang Jia, Qisheng Xu, Kele Xu, Weijun Yuan, Zhan Li, Wenqin Kuang, Ruijin Guan, Ruting Deng, Zhao Zhang, Bo wang, Suiyi Zhao, Yan Luo, Yanyan Wei, Asif Hussain Khan, Christian Micheloni, Niki Martinel
This paper reviews the NTIRE 2024 challenge on image super-resolution ($\times$4), highlighting the solutions proposed and the outcomes obtained.
no code implementations • 18 Mar 2024 • Onur Keleş, A. Murat Tekalp
In this paper, we introduce a brand new neuron model called Pade neurons (Paons), inspired by the Pade approximants, which is the best mathematical approximation of a transcendental function as a ratio of polynomials with different orders.
1 code implementation • 29 Feb 2024 • Cansu Korkmaz, A. Murat Tekalp, Zafer Dogan
Although some recent works focused on the differentiation of details and artifacts, this is a very challenging problem and a satisfactory solution is yet to be found.
no code implementations • 14 Feb 2024 • Oguzhan Gungordu, A. Murat Tekalp
Effective compression of 360$^\circ$ images, also referred to as omnidirectional images (ODIs), is of high interest for various virtual reality (VR) and related applications.
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.
no code implementations • 12 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.
1 code implementation • 4 Jul 2023 • Nasrin Rahimi, A. Murat Tekalp
Perception-distortion trade-off is well-understood for single-image super-resolution.
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.
no code implementations • 21 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.
Ranked #3 on Video Deinterlacing on MSU Deinterlacer Benchmark
no code implementations • 18 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.
no code implementations • 18 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.
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.
no code implementations • 1 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.
no code implementations • 31 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).
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 • 30 Apr 2021 • Ogun Kirmemis, A. Murat Tekalp
RDO serves well for optimization of codec performance for evaluation of the results in terms of PSNR.
no code implementations • 9 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.
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.
no code implementations • 17 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.