With the development of higher resolution contents and displays, its significant volume poses significant challenges to the goals of acquiring, transmitting, compressing and displaying high quality video content. In this paper, we propose a new deep learning video compression architecture that does not require motion estimation, which is the most expensive element of modern hybrid video compression codecs like H.264 and HEVC. Our framework exploits the regularities inherent to video motion, which we capture by using displaced frame differences as video representations to train the neural network. In addition, we propose a new space-time reconstruction network based on both an LSTM model and a UNet model, which we call LSTM-UNet. The combined network is able to efficiently capture both temporal and spatial video information, making it highly amenable for our purposes. The new video compression framework has three components: a Displacement Calculation Unit (DCU), a Displacement Compression Network (DCN), and a Frame Reconstruction Network (FRN), all of which are jointly optimized against a single perceptual loss function. The DCU obviates the need for motion estimation as in hybrid codecs, and is less expensive. In the DCN, an RNN-based network is utilized to conduct variable bit-rate encoding based on a single round of training. The LSTM-UNet is used in the FRN to learn space time differential representations of videos. Our experimental results show that our compression model, which we call the MOtionless VIdeo Codec (MOVI-Codec), learns how to efficiently compress videos without computing motion. Our experiments show that MOVI-Codec outperforms the video coding standard H.264, and is highly competitive with, and sometimes exceeds the performance of the modern global standard HEVC codec, as measured by MS-SSIM.
Banding artifacts, which manifest as staircase-like color bands on pictures or video frames, is a common distortion caused by compression of low-textured smooth regions. These false contours can be very noticeable even on high-quality videos, especially when displayed on high-definition screens. Yet, relatively little attention has been applied to this problem. Here we consider banding artifact removal as a visual enhancement problem, and accordingly, we solve it by applying a form of content-adaptive smoothing filtering followed by dithered quantization, as a post-processing module. The proposed debanding filter is able to adaptively smooth banded regions while preserving image edges and details, yielding perceptually enhanced gradient rendering with limited bit-depths. Experimental results show that our proposed debanding filter outperforms state-of-the-art false contour removing algorithms both visually and quantitatively.
High frame rate (HFR) videos are becoming increasingly common with the tremendous popularity of live, high-action streaming content such as sports. Although HFR contents are generally of very high quality, high bandwidth requirements make them challenging to deliver efficiently, while simultaneously maintaining their quality. To optimize trade-offs between bandwidth requirements and video quality, in terms of frame rate adaptation, it is imperative to understand the intricate relationship between frame rate and perceptual video quality. Towards advancing progression in this direction we designed a new subjective resource, called the LIVE-YouTube-HFR (LIVE-YT-HFR) dataset, which is comprised of 480 videos having 6 different frame rates, obtained from 16 diverse contents. In order to understand the combined effects of compression and frame rate adjustment, we also processed videos at 5 compression levels at each frame rate. To obtain subjective labels on the videos, we conducted a human study yielding 19,000 human quality ratings obtained from a pool of 85 human subjects. We also conducted a holistic evaluation of existing state-of-the-art Full and No-Reference video quality algorithms, and statistically benchmarked their performance on the new database. The LIVE-YT-HFR database has been made available online for public use and evaluation purposes, with hopes that it will help advance research in this exciting video technology direction. It may be obtained at \url{https://live.ece.utexas.edu/research/LIVE_YT_HFR/LIVE_YT_HFR/index.html}
Mean squared error (MSE) and $\ell_p$ norms have largely dominated the measurement of loss in neural networks due to their simplicity and analytical properties. However, when used to assess visual information loss, these simple norms are not highly consistent with human perception. Here, we propose a different proxy approach to optimize image analysis networks against quantitative perceptual models. Specifically, we construct a proxy network, which mimics the perceptual model while serving as a loss layer of the network.We experimentally demonstrate how this optimization framework can be applied to train an end-to-end optimized image compression network. By building on top of a modern deep image compression models, we are able to demonstrate an averaged bitrate reduction of $28.7\%$ over MSE optimization, given a specified perceptual quality (VMAF) level.
High frame rate videos are increasingly getting popular in recent years majorly driven by strong requirements by the entertainment and streaming industries to provide high quality of experiences to consumers. To achieve the best trade-off between the bandwidth requirements and video quality in terms of frame rate adaptation, it is imperative to understand the effects of frame rate on video quality. In this direction, we make two contributions: firstly we design a High Frame Rate (HFR) video database consisting of 480 videos and around 19,000 human quality ratings. We then devise a novel statistical entropic differencing method based on Generalized Gaussian Distribution model in spatial and temporal band-pass domain, which measures the difference in quality between the reference and distorted videos. The proposed design is highly generalizable and can be employed when the reference and distorted sequences have different frame rates, without any need of temporal upsampling. We show through extensive experiments that our model correlates very well with subjective scores in the HFR database and achieves state of the art performance when compared with existing methodologies.
Recent years have witnessed an explosion of user-generated content (UGC) videos shared and streamed over the Internet, thanks to the evolution of affordable and reliable consumer capture devices, and the tremendous popularity of social media platforms. Accordingly, there is a great need for accurate video quality assessment (VQA) models for UGC/consumer videos to monitor, control, and optimize this vast content. Blind quality prediction of in-the-wild videos is quite challenging, since the quality degradations of UGC content are unpredictable, complicated, and often commingled. Here we contribute to advancing the UGC-VQA problem by conducting a comprehensive evaluation of leading no-reference/blind VQA (BVQA) features and models on a fixed evaluation architecture, yielding new empirical insights on both subjective video quality studies and VQA model design. By employing a feature selection strategy on top of leading VQA model features, we are able to extract 60 of the 763 statistical features used by the leading models to create a new fusion-based BVQA model, which we dub the \textbf{VID}eo quality \textbf{EVAL}uator (VIDEVAL), that effectively balances the trade-off between VQA performance and efficiency. Our experimental results show that VIDEVAL achieves state-of-the-art performance at considerably lower computational cost than other leading models. Our study protocol also defines a reliable benchmark for the UGC-VQA problem, which we believe will facilitate further research on deep learning-based VQA modeling, as well as perceptually-optimized efficient UGC video processing, transcoding, and streaming. To promote reproducible research and public evaluation, an implementation of VIDEVAL has been made available online: \url{https://github.com/tu184044109/VIDEVAL_release}.
Banding artifact, or false contouring, is a common video compression impairment that tends to appear on large flat regions in encoded videos. These staircase-shaped color bands can be very noticeable in high-definition videos. Here we study this artifact, and propose a new distortion-specific no-reference video quality model for predicting banding artifacts, called the Blind BANding Detector (BBAND index). BBAND is inspired by human visual models. The proposed detector can generate a pixel-wise banding visibility map and output a banding severity score at both the frame and video levels. Experimental results show that our proposed method outperforms state-of-the-art banding detection algorithms and delivers better consistency with subjective evaluations.
Many objective video quality assessment (VQA) algorithms include a key step of temporal pooling of frame-level quality scores. However, less attention has been paid to studying the relative efficiencies of different pooling methods on no-reference (blind) VQA. Here we conduct a large-scale comparative evaluation to assess the capabilities and limitations of multiple temporal pooling strategies on blind VQA of user-generated videos. The study yields insights and general guidance regarding the application and selection of temporal pooling models. In addition, we also propose an ensemble pooling model built on top of high-performing temporal pooling models. Our experimental results demonstrate the relative efficacies of the evaluated temporal pooling models, using several popular VQA algorithms, and evaluated on two recent large-scale natural video quality databases. In addition to the new ensemble model, we provide a general recipe for applying temporal pooling of frame-based quality predictions.
The use of $\ell_p$ $(p=1,2)$ norms has largely dominated the measurement of loss in neural networks due to their simplicity and analytical properties. However, when used to assess the loss of visual information, these simple norms are not very consistent with human perception. Here, we describe a different "proximal" approach to optimize image analysis networks against quantitative perceptual models. Specifically, we construct a proxy network, broadly termed ProxIQA, which mimics the perceptual model while serving as a loss layer of the network. We experimentally demonstrate how this optimization framework can be applied to train an end-to-end optimized image compression network. By building on top of an existing deep image compression model, we are able to demonstrate a bitrate reduction of as much as $31\%$ over MSE optimization, given a specified perceptual quality (VMAF) level.
In VP9 video codec, the sizes of blocks are decided during encoding by recursively partitioning 64$\times$64 superblocks using rate-distortion optimization (RDO). This process is computationally intensive because of the combinatorial search space of possible partitions of a superblock. Here, we propose a deep learning based alternative framework to predict the intra-mode superblock partitions in the form of a four-level partition tree, using a hierarchical fully convolutional network (H-FCN). We created a large database of VP9 superblocks and the corresponding partitions to train an H-FCN model, which was subsequently integrated with the VP9 encoder to reduce the intra-mode encoding time. The experimental results establish that our approach speeds up intra-mode encoding by 69.7% on average, at the expense of a 1.71% increase in the Bjontegaard-Delta bitrate (BD-rate). While VP9 provides several built-in speed levels which are designed to provide faster encoding at the expense of decreased rate-distortion performance, we find that our model is able to outperform the fastest recommended speed level of the reference VP9 encoder for the good quality intra encoding configuration, in terms of both speedup and BD-rate.