arXiv subjects

A. Murat Tekalp

Publications and source records attributed to A. Murat Tekalp.

At least 37 records · Page 2Linked to original sources

arXiv2023

Spatio-Temporal Perception-Distortion Trade-off in Learned Video SR

Perception-distortion trade-off is well-understood for single-image super-resolution. However, its extension to video super-resolution (VSR) is not straightforward, since popular perceptual measures only evaluate naturalness of spatial textures and do not take naturalness of flow (temporal coherence) into account. To this effect, we propose a new measure of spatio-temporal perceptual video quality emphasizing naturalness of optical flow via the perceptual straightness hypothesis (PSH) for meaningful spatio-temporal perception-distortion trade-off. We also propose a new architecture for perceptual VSR (PSVR) to explicitly enforce naturalness of flow to achieve realistic spatio-temporal perception-distortion trade-off according to the proposed measures. Experimental results with PVSR support the hypothesis that a meaningful perception-distortion tradeoff for video should account for the naturalness of motion in addition to naturalness of texture.

eess.IV↗

arXiv2023

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

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. This paper advances the state-of-the-art by proposing an adaptive motion-compensation model for end-to-end rate-distortion optimized hierarchical bi-directional video compression. In particular, we propose two novelties: i) a multi-scale deformable alignment scheme at the feature level combined with multi-scale conditional coding, ii) motion-content adaptive inference. In addition, we employ a gain unit, which enables a single model to operate at multiple rate-distortion operating points. We also exploit the gain unit to control bit allocation among intra-coded vs. bi-directionally coded frames by fine tuning corresponding models for truly flexible-rate learned video coding. Experimental results demonstrate state-of-the-art rate-distortion performance exceeding those of all prior art in learned video coding.

eess.IV↗

arXiv2022

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

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. This is despite deinterlacing is well-suited for supervised learning from synthetic data since the degradation model is known and fixed. In this paper, we propose a novel multi-field full frame-rate deinterlacing network, which adapts the state-of-the-art superresolution approaches to the deinterlacing task. Our model aligns features from adjacent fields to a reference field (to be deinterlaced) using both deformable convolution residual blocks and self attention. Our extensive experimental results demonstrate that the proposed method provides state-of-the-art deinterlacing results in terms of both numerical and perceptual performance. At the time of writing, our model ranks first in the Full FrameRate LeaderBoard at https://videoprocessing.ai/benchmarks/deinterlacer.html

eess.IV↗

arXiv2022

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

Flow-based generative super-resolution (SR) models learn to produce a diverse set of feasible SR solutions, called the SR space. Diversity of SR solutions increases with the temperature ($τ$) of latent variables, which introduces random variations of texture among sample solutions, resulting in visual artifacts and low fidelity. In this paper, we present a simple but effective image ensembling/fusion approach to obtain a single SR image eliminating random artifacts and improving fidelity without significantly compromising perceptual quality. We achieve this by benefiting from a diverse set of feasible photo-realistic solutions in the SR space spanned by flow models. We propose different image ensembling and fusion strategies which offer multiple paths to move sample solutions in the SR space to more desired destinations in the perception-distortion plane in a controllable manner depending on the fidelity vs. perceptual quality requirements of the task at hand. Experimental results demonstrate that our image ensembling/fusion strategy achieves more promising perception-distortion trade-off compared to sample SR images produced by flow models and adversarially trained models in terms of both quantitative metrics and visual quality.

cs.CV↗

arXiv2022

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

Assuming a known degradation model, the performance of a learned image super-resolution (SR) model depends on how well the variety of image characteristics within the training set matches those in the test set. 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. Hence, in general, a single SR model cannot generalize well enough for all types of image content. In this work, we show that training multiple SR models for different classes of images (e.g., for text, texture, etc.) to exploit class-specific image priors and employing a post-processing network that learns how to best fuse the outputs produced by these multiple SR models surpasses the performance of state-of-the-art generic SR models. Experimental results clearly demonstrate that the proposed multiple-model SR (MMSR) approach significantly outperforms a single pre-trained state-of-the-art SR model both quantitatively and visually. It even exceeds the performance of the best single class-specific SR model trained on similar text or texture images.

cs.CV↗

arXiv2022

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

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. As an improvement, we combine motion estimation and prediction modules and compress refined residual motion vectors for improved rate-distortion performance. As novel addition, we adapted the gain unit proposed for image compression to flexible-rate video compression in two ways: first, the gain unit enables a single encoder model to operate at multiple rate-distortion operating points; second, we exploit the gain unit to control bit allocation among intra-coded vs. bi-directionally coded frames by fine tuning corresponding models for truly flexible-rate learned video coding. Experimental results demonstrate that we obtain state-of-the-art rate-distortion performance exceeding those of all prior art in learned video coding.

eess.IV↗

arXiv2021

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

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. Learned VC allows end-to-end rate-distortion (R-D) optimized training of nonlinear transform, motion and entropy model simultaneously. Most works on learned VC consider end-to-end optimization of a sequential video codec based on R-D loss averaged over pairs of successive frames. It is well-known in conventional VC that hierarchical, bi-directional coding outperforms sequential compression because of its ability to use both past and future reference frames. This paper proposes a learned hierarchical bi-directional video codec (LHBDC) that combines the benefits of hierarchical motion-compensated prediction and end-to-end optimization. Experimental results show that we achieve the best R-D results that are reported for learned VC schemes to date in both PSNR and MS-SSIM. Compared to conventional video codecs, the R-D performance of our end-to-end optimized codec outperforms those of both x265 and SVT-HEVC encoders ("veryslow" preset) in PSNR and MS-SSIM as well as HM 16.23 reference software in MS-SSIM. We present ablation studies showing performance gains due to proposed novel tools such as learned masking, flow-field subsampling, and temporal flow vector prediction. The models and instructions to reproduce our results can be found in https://github.com/makinyilmaz/LHBDC/

eess.IV↗

arXiv2021

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

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. Recently, an approach to first map images downsampled by unknown filters to bicubicly downsampled look-alike images was proposed to successfully super-resolve such images. In this paper, we show that any inverse problem can be formulated by first mapping the input degraded images to an intermediate domain, and then training a second network to form output images from these intermediate images. Furthermore, the best intermediate domain may vary according to the task. Our experimental results demonstrate that this two-stage domain-adapted training strategy does not only achieve better results on a given class of unknown degradations but can also generalize to other unseen classes of degradations better.

eess.IV↗

arXiv2021

Self-Organized Residual Blocks for Image Super-Resolution

It has become a standard practice to use the convolutional networks (ConvNet) with RELU non-linearity in image restoration and super-resolution (SR). Although the universal approximation theorem states that a multi-layer neural network can approximate any non-linear function with the desired precision, it does not reveal the best network architecture to do so. Recently, operational neural networks (ONNs) that choose the best non-linearity from a set of alternatives, and their "self-organized" variants (Self-ONN) that approximate any non-linearity via Taylor series have been proposed to address the well-known limitations and drawbacks of conventional ConvNets such as network homogeneity using only the McCulloch-Pitts neuron model. In this paper, we propose the concept of self-organized operational residual (SOR) blocks, and present hybrid network architectures combining regular residual and SOR blocks to strike a balance between the benefits of stronger non-linearity and the overall number of parameters. The experimental results demonstrate that the~proposed architectures yield performance improvements in both PSNR and perceptual metrics.

eess.IV↗

arXiv2021

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

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. Recently, Operational Neural Networks (ONNs) that learn the best non-linearity from a set of alternatives, and their self-organized variants, Self-ONNs, that approximate any non-linearity via Taylor series have been proposed to address the limitations of convolutional layers and a fixed nonlinear activation. In this paper, we propose to replace the convolutional and GDN layers in the variational autoencoder with self-organized operational layers, and propose a novel self-organized variational autoencoder (Self-VAE) architecture that benefits from stronger non-linearity. The experimental results demonstrate that the proposed Self-VAE yields improvements in both rate-distortion performance and perceptual image quality.

eess.IV↗

arXiv2021

DFPN: Deformable Frame Prediction Network

Learned frame prediction is a current problem of interest in computer vision and video compression. Although several deep network architectures have been proposed for learned frame prediction, to the best of our knowledge, there is no work based on using deformable convolutions for frame prediction. To this effect, we propose a deformable frame prediction network (DFPN) for task oriented implicit motion modeling and next frame prediction. Experimental results demonstrate that the proposed DFPN model achieves state of the art results in next frame prediction. Our models and results are available at https://github.com/makinyilmaz/DFPN.

cs.CV↗

arXiv2021

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

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 {\it GOP coder} outperforms the state-of-the-art end-to-end optimized learned sequential compression as expected.

eess.IV↗

arXiv2021

A Practical Approach for Rate-Distortion-Perception Analysis in Learned Image Compression

Rate-distortion optimization (RDO) of codecs, where distortion is quantified by the mean-square error, has been a standard practice in image/video compression over the years. RDO serves well for optimization of codec performance for evaluation of the results in terms of PSNR. However, it is well known that the PSNR does not correlate well with perceptual evaluation of images; hence, RDO is not well suited for perceptual optimization of codecs. Recently, rate-distortion-perception trade-off has been formalized by taking the Kullback-Leibner (KL) divergence between the distributions of the original and reconstructed images as a perception measure. Learned image compression methods that simultaneously optimize rate, mean-square loss, VGG loss, and an adversarial loss were proposed. Yet, there exists no easy approach to fix the rate, distortion or perception at a desired level in a practical learned image compression solution to perform an analysis of the trade-off between rate, distortion and perception measures. In this paper, we propose a practical approach to fix the rate to carry out perception-distortion analysis at a fixed rate in order to perform perceptual evaluation of image compression results in a principled manner. Experimental results provide several insights for practical rate-distortion-perception analysis in learned image compression.

eess.IV↗

arXiv2021

On the Computation of PSNR for a Set of Images or Video

When comparing learned image/video restoration and compression methods, it is common to report peak-signal to noise ratio (PSNR) results. However, there does not exist a generally agreed upon practice to compute PSNR for sets of images or video. Some authors report average of individual image/frame PSNR, which is equivalent to computing a single PSNR from the geometric mean of individual image/frame mean-square error (MSE). Others compute a single PSNR from the arithmetic mean of frame MSEs for each video. Furthermore, some compute the MSE/PSNR of Y-channel only, while others compute MSE/PSNR for RGB channels. This paper investigates different approaches to computing PSNR for sets of images, single video, and sets of video and the relation between them. We show the difference between computing the PSNR based on arithmetic vs. geometric mean of MSE depends on the distribution of MSE over the set of images or video, and that this distribution is task-dependent. In particular, these two methods yield larger differences in restoration problems, where the MSE is exponentially distributed and smaller differences in compression problems, where the MSE distribution is narrower. We hope this paper will motivate the community to clearly describe how they compute reported PSNR values to enable consistent comparison.

eess.IV↗

arXiv2021

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

Recent works have shown that learned models can achieve significant performance gains, especially in terms of perceptual quality measures, over traditional methods. Hence, the state of the art in image restoration and compression is getting redefined. This special issue covers the state of the art in learned image/video restoration and compression to promote further progress in innovative architectures and training methods for effective and efficient networks for image/video restoration and compression.

eess.IV↗

arXiv2020

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

We analyze the performance of feedforward vs. recurrent neural network (RNN) architectures and associated training methods for learned frame prediction. To this effect, we trained a residual fully convolutional neural network (FCNN), a convolutional RNN (CRNN), and a convolutional long short-term memory (CLSTM) network for next frame prediction using the mean square loss. We performed both stateless and stateful training for recurrent networks. Experimental results show that the residual FCNN architecture performs the best in terms of peak signal to noise ratio (PSNR) at the expense of higher training and test (inference) computational complexity. The CRNN can be trained stably and very efficiently using the stateful truncated backpropagation through time procedure, and it requires an order of magnitude less inference runtime to achieve near real-time frame prediction with an acceptable performance.

cs.CV↗

arXiv2020

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

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. Frame differences given learned frame predictions are encoded by a standard still-image (intra) codec. Experimental results show that the rate-distortion performance of the simple codec with symmetric complexity is on average better than that of x264 codec on 10 MPEG test videos, but does not yet reach the level of x265 codec. This result demonstrates the power of learned frame prediction (LFP), since unlike motion compensation, LFP does not use information from the current picture. The implications of training with L1, L2, or combined L2 and adversarial loss on prediction performance and compression efficiency are analyzed.

eess.IV↗

arXiv2020

Realizing a Low-Power Head-Mounted Phase-Only Holographic Display by Light-Weight Compression

Head-mounted holographic displays (HMHD) are projected to be the first commercial realization of holographic video display systems. HMHDs use liquid crystal on silicon (LCoS) spatial light modulators (SLM), which are best suited to display phase-only holograms (POH). The performance/watt requirement of a monochrome, 60 fps Full HD, 2-eye, POH HMHD system is about 10 TFLOPS/W, which is orders of magnitude higher than that is achievable by commercially available mobile processors. To mitigate this compute power constraint, display-ready POHs shall be generated on a nearby server and sent to the HMHD in compressed form over a wireless link. This paper discusses design of a feasible HMHD-based augmented reality system, focusing on compression requirements and per-pixel rate-distortion trade-off for transmission of display-ready POH from the server to HMHD. Since the decoder in the HMHD needs to operate on low power, only coding methods that have low-power decoder implementation are considered. Effects of 2D phase unwrapping and flat quantization on compression performance are also reported. We next propose a versatile PCM-POH codec with progressive quantization that can adapt to SLM-dynamic-range and available bitrate, and features per-pixel rate-distortion control to achieve acceptable POH quality at target rates of 60-200 Mbit/s that can be reliably achieved by current wireless technologies. Our results demonstrate feasibility of realizing a low-power, quality-ensured, multi-user, interactive HMHD augmented reality system with commercially available components using the proposed adaptive compression of display-ready POH with light-weight decoding.

eess.IV↗