Anil Kokaram

Darren Ramsook, Anil Kokaram

Image based Deep Feature Quality Metrics (DFQMs) have been shown to better correlate with subjective perceptual scores over traditional metrics. The fundamental focus of these DFQMs is to exploit internal representations from a large scale classification network as the metric feature space. Previously, no attention has been given to the problem of identifying which layers are most perceptually relevant. In this paper we present a new method for selecting perceptually relevant layers from such a network, based on a neuroscience interpretation of layer behaviour. The selected layers are treated as a hyperparameter to the critic network in a W-GAN. The critic uses the output from these layers in the preliminary stages to extract perceptual information. A video enhancement network is trained adversarially with this critic. Our results show that the introduction of these selected features into the critic yields up to 10% (FID) and 15% (KID) performance increase against other critic networks that do not exploit the idea of optimised feature selection.

Michael O'Byrne, Vibhoothi, Mark Sugrue et al.

This study examines the relationship between H.264 video compression and the performance of an object detection network (YOLOv5). We curated a set of 50 surveillance videos and annotated targets of interest (people, bikes, and vehicles). Videos were encoded at 5 quality levels using Constant Rate Factor (CRF) values in the set {22,32,37,42,47}. YOLOv5 was applied to compressed videos and detection performance was analyzed at each CRF level. Test results indicate that the detection performance is generally robust to moderate levels of compression; using a CRF value of 37 instead of 22 leads to significantly reduced bitrates/file sizes without adversely affecting detection performance. However, detection performance degrades appreciably at higher compression levels, especially in complex scenes with poor lighting and fast-moving targets. Finally, retraining YOLOv5 on compressed imagery gives up to a 1% improvement in F1 score when applied to highly compressed footage.

Uditangshu Aurangabadkar, Darren Ramsook, Anil Kokaram

The success of modern Deep Neural Network (DNN) approaches can be attributed to the use of complex optimization criteria beyond standard losses such as mean absolute error (MAE) or mean squared error (MSE). In this work, we propose a novel method of utilising a no-reference sharpness metric Q introduced by Zhu and Milanfar for removing out-of-focus blur from images. We also introduce a novel dataset of real-world out-of-focus images for assessing restoration models. Our fine-tuned method produces images with a 7.5 % increase in perceptual quality (LPIPS) as compared to a standard model trained only on MAE. Furthermore, we observe a 6.7 % increase in Q (reflecting sharper restorations) and 7.25 % increase in PSNR over most state-of-the-art (SOTA) methods.

Julien Zouein, Vibhoothi Vibhoothi, François Pitié et al.

3D Gaussian Splatting (3DGS) has emerged as a prominent framework for real-time, photorealistic scene reconstruction, offering significant speed-ups over Neural Radiance Fields (NeRF). However, the fidelity of 3DGS representations remains heavily dependent on the quality of the initial point cloud. While standard Structure-from-Motion (SfM) pipelines using COLMAP provide adequate initialisation, they often suffer from high computational costs and sparsity in textureless regions, which degrades subsequent reconstruction accuracy and convergence speed. In this work, we introduce an AV1-based feature detection and matching pipeline that significantly reduces SfM processing overhead. By leveraging motion vectors inherent to the AV1 video codec, we bypass computationally expensive exhaustive matching while maintaining geometric robustness. Our pipeline produces substantially denser point clouds, with up to eight times as many points as classical SfM. We demonstrate that this enhanced initialisation directly improves 3DGS performance, yielding an 9-point increase in VMAF and a 63% average reduction in training time required to reach baseline quality. The project page: https://sigmedia.tv/AV1-3DGS.github.io/

Conall Daly, Darren Ramsook, Anil Kokaram

Video frame interpolation is a fundamental tool for temporal video enhancement, but existing quality metrics struggle to evaluate the perceptual impact of interpolation artefacts effectively. Metrics like PSNR, SSIM and LPIPS ignore temporal coherence. State-of-the-art quality metrics tailored towards video frame interpolation, like FloLPIPS, have been developed but suffer from computational inefficiency that limits their practical application. We present $\text{PSNR}_{\text{DIV}}$, a novel full-reference quality metric that enhances PSNR through motion divergence weighting, a technique adapted from archival film restoration where it was developed to detect temporal inconsistencies. Our approach highlights singularities in motion fields which is then used to weight image errors. Evaluation on the BVI-VFI dataset (180 sequences across multiple frame rates, resolutions and interpolation methods) shows $\text{PSNR}_{\text{DIV}}$ achieves statistically significant improvements: +0.09 Pearson Linear Correlation Coefficient over FloLPIPS, while being 2.5$\times$ faster and using 4$\times$ less memory. Performance remains consistent across all content categories and are robust to the motion estimator used. The efficiency and accuracy of $\text{PSNR}_{\text{DIV}}$ enables fast quality evaluation and practical use as a loss function for training neural networks for video frame interpolation tasks. An implementation of our metric is available at www.github.com/conalld/psnr-div.

Julien Zouein, Vibhoothi Vibhoothi, Anil Kokaram

This paper presents a comprehensive analysis of motion vectors extracted from AV1-encoded video streams and their application in accelerating optical flow estimation. We demonstrate that motion vectors from AV1 video codec can serve as a high-quality and computationally efficient substitute for traditional optical flow, a critical but often resource-intensive component in many computer vision pipelines. Our primary contributions are twofold. First, we provide a detailed comparison of motion vectors from both AV1 and HEVC against ground-truth optical flow, establishing their fidelity. In particular we show the impact of encoder settings on motion estimation fidelity and make recommendations about the optimal settings. Second, we show that using these extracted AV1 motion vectors as a "warm-start" for a state-of-the-art deep learning-based optical flow method, RAFT, significantly reduces the time to convergence while achieving comparable accuracy. Specifically, we observe a four-fold speedup in computation time with only a minor trade- off in end-point error. These findings underscore the potential of reusing motion vectors from compressed video as a practical and efficient method for a wide range of motion-aware computer vision applications.

Julien Zouein, Hossein Javidnia, François Pitié et al.

We repurpose AV1 motion vectors to produce dense sub-pixel correspondences and short tracks filtered by cosine consistency. On short videos, this compressed-domain front end runs comparably to sequential SIFT while using far less CPU, and yields denser matches with competitive pairwise geometry. As a small SfM demo on a 117-frame clip, MV matches register all images and reconstruct 0.46-0.62M points at 0.51-0.53,px reprojection error; BA time grows with match density. These results show compressed-domain correspondences are a practical, resource-efficient front end with clear paths to scaling in full pipelines.

Vibhoothi Vibhoothi, François Pitié, Anil Kokaram

In the last decade, video workflows in the cinema production ecosystem have presented new use cases for video streaming technology. These new workflows, e.g. in On-set Virtual Production, present the challenge of requiring precise quality control and energy efficiency. Existing approaches to transcoding often fall short of these requirements, either due to a lack of quality control or computational overhead. To fill this gap, we present a lightweight neural network (LiteVPNet) for accurately predicting Quantisation Parameters for NVENC AV1 encoders that achieve a specified VMAF score. We use low-complexity features, including bitstream characteristics, video complexity measures, and CLIP-based semantic embeddings. Our results demonstrate that LiteVPNet achieves mean VMAF errors below 1.2 points across a wide range of quality targets. Notably, LiteVPNet achieves VMAF errors within 2 points for over 87% of our test corpus, c.f. approx 61% with state-of-the-art methods. LiteVPNet's performance across various quality regions highlights its applicability for enhancing high-value content transport and streaming for more energy-efficient, high-quality media experiences.

Conall Daly, Darren Ramsook, Anil Kokaram

Video frame interpolation (VFI) offers a way to generate intermediate frames between consecutive frames of a video sequence. Although the development of advanced frame interpolation algorithms has received increased attention in recent years, assessing the perceptual quality of interpolated content remains an ongoing area of research. In this paper, we investigate simple ways to process motion fields, with the purposes of using them as video quality metric for evaluating frame interpolation algorithms. We evaluate these quality metrics using the BVI-VFI dataset which contains perceptual scores measured for interpolated sequences. From our investigation we propose a motion metric based on measuring the divergence of motion fields. This metric correlates reasonably with these perceptual scores (PLCC=0.51) and is more computationally efficient (x2.7 speedup) compared to FloLPIPS (a well known motion-based metric). We then use our new proposed metrics to evaluate a range of state of the art frame interpolation metrics and find our metrics tend to favour more perceptual pleasing interpolated frames that may not score highly in terms of PSNR or SSIM.

Conall Daly, Anil Kokaram

Many methods exist for frame synthesis in image sequences but can be broadly categorised into frame interpolation and view synthesis techniques. Fundamentally, both frame interpolation and view synthesis tackle the same task, interpolating a frame given surrounding frames in time or space. However, most frame interpolation datasets focus on temporal aspects with single cameras moving through time and space, while view synthesis datasets are typically biased toward stereoscopic depth estimation use cases. This makes direct comparison between view synthesis and frame interpolation methods challenging. In this paper, we develop a novel multi-camera dataset using a custom-built dense linear camera array to enable fair comparison between these approaches. We evaluate classical and deep learning frame interpolators against a view synthesis method (3D Gaussian Splatting) for the task of view in-betweening. Our results reveal that deep learning methods do not significantly outperform classical methods on real image data, with 3D Gaussian Splatting actually underperforming frame interpolators by as much as 3.5 dB PSNR. However, in synthetic scenes, the situation reverses -- 3D Gaussian Splatting outperforms frame interpolation algorithms by almost 5 dB PSNR at a 95% confidence level.

Xin Shu, Vibhoothi Vibhoothi, Anil Kokaram

Predicting the computational cost of compressing/transcoding clips in a video corpus is important for resource management of cloud services and VOD (Video On Demand) providers. Currently, customers of cloud video services are unaware of the cost of transcoding their files until the task is completed. Previous work concentrated on predicting perclip compression time, and thus estimating the cost of video compression. In this work, we propose new Machine Learning (ML) systems which predict cost for the entire corpus instead. This is a more appropriate goal since users are not interested in per-clip cost but instead the cost for the whole corpus. In this work, we evaluate our systems with respect to two video codecs (x264, x265) and a novel high-quality video corpus. We find that the accuracy of aggregate time prediction for a video corpus more than two times better than using per-clip predictions. Furthermore, we present an online inference framework in which we update the ML models as files are processed. A consideration of video compute overhead and appropriate choice of ML predictor for each fraction of corpus completed yields a prediction error of less than 5%. This is approximately two times better than previous work which proposed generalised predictors.

Uditangshu Aurangabadkar, Anil Kokaram

The field of image deblurring has seen tremendous progress with the rise of deep learning models. These models, albeit efficient, are computationally expensive and energy consuming. Dictionary based learning approaches have shown promising results in image denoising and Single Image Super-Resolution. We propose an extension of the Rapid and Accurate Image Super-Resolution (RAISR) algorithm introduced by Isidoro, Romano and Milanfar for the task of out-of-focus blur removal. We define a sharpness quality measure which aligns well with the perceptual quality of an image. A metric based blending strategy based on asset allocation management is also proposed. Our method demonstrates an average increase of approximately 13% (PSNR) and 10% (SSIM) compared to popular deblurring methods. Furthermore, our blending scheme curtails ringing artefacts post restoration.

Chao Chen, Yao-Chung Lin, Anil Kokaram et al.

HTTP video streaming is in wide use to deliver video over the Internet. With HTTP adaptive steaming, a video playback dynamically selects a video stream from a pre-encoded representation based on available bandwidth and viewport (screen) size. The viewer's video quality is therefore influenced by the encoded bitrates. We minimize the average delivered bitrate subject to a quality lower bound on a per-chunk basis by modeling the probability that a player selects a particular encoding. Through simulation and real-world experiments, the proposed method saves 9.6% of bandwidth while average delivered video quality comparing with state of the art while keeping average delivered video quality.