David Bull

Duolikun Danier, Fan Zhang, David Bull

Existing works on video frame interpolation (VFI) mostly employ deep neural networks that are trained by minimizing the L1, L2, or deep feature space distance (e.g. VGG loss) between their outputs and ground-truth frames. However, recent works have shown that these metrics are poor indicators of perceptual VFI quality. Towards developing perceptually-oriented VFI methods, in this work we propose latent diffusion model-based VFI, LDMVFI. This approaches the VFI problem from a generative perspective by formulating it as a conditional generation problem. As the first effort to address VFI using latent diffusion models, we rigorously benchmark our method on common test sets used in the existing VFI literature. Our quantitative experiments and user study indicate that LDMVFI is able to interpolate video content with favorable perceptual quality compared to the state of the art, even in the high-resolution regime. Our code is available at https://github.com/danier97/LDMVFI.

Duolikun Danier, Fan Zhang, David Bull

Video frame interpolation (VFI) is a fundamental research topic in video processing, which is currently attracting increased attention across the research community. While the development of more advanced VFI algorithms has been extensively researched, there remains little understanding of how humans perceive the quality of interpolated content and how well existing objective quality assessment methods perform when measuring the perceived quality. In order to narrow this research gap, we have developed a new video quality database named BVI-VFI, which contains 540 distorted sequences generated by applying five commonly used VFI algorithms to 36 diverse source videos with various spatial resolutions and frame rates. We collected more than 10,800 quality ratings for these videos through a large scale subjective study involving 189 human subjects. Based on the collected subjective scores, we further analysed the influence of VFI algorithms and frame rates on the perceptual quality of interpolated videos. Moreover, we benchmarked the performance of 33 classic and state-of-the-art objective image/video quality metrics on the new database, and demonstrated the urgent requirement for more accurate bespoke quality assessment methods for VFI. To facilitate further research in this area, we have made BVI-VFI publicly available at https://github.com/danier97/BVI-VFI-database.

Ho Man Kwan, Ge Gao, Fan Zhang et al.

Learning-based video compression is currently a popular research topic, offering the potential to compete with conventional standard video codecs. In this context, Implicit Neural Representations (INRs) have previously been used to represent and compress image and video content, demonstrating relatively high decoding speed compared to other methods. However, existing INR-based methods have failed to deliver rate quality performance comparable with the state of the art in video compression. This is mainly due to the simplicity of the employed network architectures, which limit their representation capability. In this paper, we propose HiNeRV, an INR that combines light weight layers with novel hierarchical positional encodings. We employs depth-wise convolutional, MLP and interpolation layers to build the deep and wide network architecture with high capacity. HiNeRV is also a unified representation encoding videos in both frames and patches at the same time, which offers higher performance and flexibility than existing methods. We further build a video codec based on HiNeRV and a refined pipeline for training, pruning and quantization that can better preserve HiNeRV's performance during lossy model compression. The proposed method has been evaluated on both UVG and MCL-JCV datasets for video compression, demonstrating significant improvement over all existing INRs baselines and competitive performance when compared to learning-based codecs (72.3% overall bit rate saving over HNeRV and 43.4% over DCVC on the UVG dataset, measured in PSNR).

Xinyi Wang, Angeliki Katsenou, David Bull

With the rapid growth of User-Generated Content (UGC) exchanged between users and sharing platforms, the need for video quality assessment in the wild is increasingly evident. UGC is typically acquired using consumer devices and undergoes multiple rounds of compression (transcoding) before reaching the end user. Therefore, traditional quality metrics that employ the original content as a reference are not suitable. In this paper, we propose ReLaX-VQA, a novel No-Reference Video Quality Assessment (NR-VQA) model that aims to address the challenges of evaluating the quality of diverse video content without reference to the original uncompressed videos. ReLaX-VQA uses frame differences to select spatio-temporal fragments intelligently together with different expressions of spatial features associated with the sampled frames. These are then used to better capture spatial and temporal variabilities in the quality of neighbouring frames. Furthermore, the model enhances abstraction by employing layer-stacking techniques in deep neural network features from Residual Networks and Vision Transformers. Extensive testing across four UGC datasets demonstrates that ReLaX-VQA consistently outperforms existing NR-VQA methods, achieving an average SRCC of 0.8658 and PLCC of 0.8873. Open-source code and trained models that will facilitate further research and applications of NR-VQA can be found at https://github.com/xinyiW915/ReLaX-VQA.

Xinyi Wang, Angeliki Katsenou, David Bull

The volume of User Generated Content (UGC) has increased in recent years. The challenge with this type of content is assessing its quality. So far, the state-of-the-art metrics are not exhibiting a very high correlation with perceptual quality. In this paper, we explore state-of-the-art metrics that extract/combine natural scene statistics and deep neural network features. We experiment with these by introducing saliency maps to improve perceptibility. We train and test our models using public datasets, namely, YouTube-UGC and KoNViD-1k. Preliminary results indicate that high correlations are achieved by using only deep features while adding saliency is not always boosting the performance. Our results and code will be made publicly available to serve as a benchmark for the research community and can be found on our project page: https://github.com/xinyiW915/SPIE-2023-Supplementary.

Duolikun Danier, Fan Zhang, David Bull

Video frame interpolation (VFI) serves as a useful tool for many video processing applications. Recently, it has also been applied in the video compression domain for enhancing both conventional video codecs and learning-based compression architectures. While there has been an increased focus on the development of enhanced frame interpolation algorithms in recent years, the perceptual quality assessment of interpolated content remains an open field of research. In this paper, we present a bespoke full reference video quality metric for VFI, FloLPIPS, that builds on the popular perceptual image quality metric, LPIPS, which captures the perceptual degradation in extracted image feature space. In order to enhance the performance of LPIPS for evaluating interpolated content, we re-designed its spatial feature aggregation step by using the temporal distortion (through comparing optical flows) to weight the feature difference maps. Evaluated on the BVI-VFI database, which contains 180 test sequences with various frame interpolation artefacts, FloLPIPS shows superior correlation performance (with statistical significance) with subjective ground truth over 12 popular quality assessors. To facilitate further research in VFI quality assessment, our code is publicly available at https://danier97.github.io/FloLPIPS.

Xinyi Wang, Angeliki Katsenou, Junxiao Shen et al.

The prevalence of user-generated content (UGC) on platforms such as YouTube and TikTok has rendered no-reference (NR) perceptual video quality assessment (VQA) vital for optimizing video delivery. Nonetheless, the characteristics of non-professional acquisition and the subsequent transcoding of UGC video on sharing platforms present significant challenges for NR-VQA. Although NR-VQA models attempt to infer mean opinion scores (MOS), their modeling of subjective scores for compressed content remains limited due to the absence of fine-grained perceptual annotations of artifact types. To address these challenges, we propose CAMP-VQA, a novel NR-VQA framework that exploits the semantic understanding capabilities of large vision-language models. Our approach introduces a quality-aware prompting mechanism that integrates video metadata (e.g., resolution, frame rate, bitrate) with key fragments extracted from inter-frame variations to guide the BLIP-2 pretraining approach in generating fine-grained quality captions. A unified architecture has been designed to model perceptual quality across three dimensions: semantic alignment, temporal characteristics, and spatial characteristics. These multimodal features are extracted and fused, then regressed to video quality scores. Extensive experiments on a wide variety of UGC datasets demonstrate that our model consistently outperforms existing NR-VQA methods, achieving improved accuracy without the need for costly manual fine-grained annotations. Our method achieves the best performance in terms of average rank and linear correlation (SRCC: 0.928, PLCC: 0.938) compared to state-of-the-art methods. The source code and trained models, along with a user-friendly demo, are available at: https://github.com/xinyiW915/CAMP-VQA.

Paul Hill, Nantheera Anantrasirichai, Alin Achim et al.

The influence of atmospheric turbulence on acquired imagery makes image interpretation and scene analysis extremely difficult and reduces the effectiveness of conventional approaches for classifying and tracking objects of interest in the scene. Restoring a scene distorted by atmospheric turbulence is also a challenging problem. The effect, which is caused by random, spatially varying perturbations, makes conventional model-based approaches difficult and, in most cases, impractical due to complexity and memory requirements. Deep learning approaches offer faster operation and are capable of implementation on small devices. This paper reviews the characteristics of atmospheric turbulence and its impact on acquired imagery. It compares the performance of various state-of-the-art deep neural networks, including Transformers, SWIN and Mamba, when used to mitigate spatio-temporal image distortions.

Ruirui Lin, Nantheera Anantrasirichai, Guoxi Huang et al.

Low-light videos often exhibit spatiotemporal incoherent noise, compromising visibility and performance in computer vision applications. One significant challenge in enhancing such content using deep learning is the scarcity of training data. This paper introduces a novel low-light video dataset, consisting of 40 scenes with various motion scenarios under two distinct low-lighting conditions, incorporating genuine noise and temporal artifacts. We provide fully registered ground truth data captured in normal light using a programmable motorized dolly and refine it via an image-based approach for pixel-wise frame alignment across different light levels. We provide benchmarks based on four different technologies: convolutional neural networks, transformers, diffusion models, and state space models (mamba). Our experimental results demonstrate the significance of fully registered video pairs for low-light video enhancement (LLVE) and the comprehensive evaluation shows that the models trained with our dataset outperform those trained with the existing datasets. Our dataset and links to benchmarks are publicly available at https://doi.org/10.21227/mzny-8c77.

Ho Man Kwan, Ge Gao, Fan Zhang et al.

Recent advances in implicit neural representation (INR)-based video coding have demonstrated its potential to compete with both conventional and other learning-based approaches. With INR methods, a neural network is trained to overfit a video sequence, with its parameters compressed to obtain a compact representation of the video content. However, although promising results have been achieved, the best INR-based methods are still out-performed by the latest standard codecs, such as VVC VTM, partially due to the simple model compression techniques employed. In this paper, rather than focusing on representation architectures as in many existing works, we propose a novel INR-based video compression framework, Neural Video Representation Compression (NVRC), targeting compression of the representation. Based on the novel entropy coding and quantization models proposed, NVRC, for the first time, is able to optimize an INR-based video codec in a fully end-to-end manner. To further minimize the additional bitrate overhead introduced by the entropy models, we have also proposed a new model compression framework for coding all the network, quantization and entropy model parameters hierarchically. Our experiments show that NVRC outperforms many conventional and learning-based benchmark codecs, with a 24% average coding gain over VVC VTM (Random Access) on the UVG dataset, measured in PSNR. As far as we are aware, this is the first time an INR-based video codec achieving such performance. The implementation of NVRC will be released.

Siyue Teng, Yuxuan Jiang, Ge Gao et al.

Recent advances in video compression have seen significant coding performance improvements with the development of new standards and learning-based video codecs. However, most of these works focus on application scenarios that allow a certain amount of system delay (e.g., Random Access mode in MPEG codecs), which is not always acceptable for live delivery. This paper conducts a comparative study of state-of-the-art conventional and learned video coding methods based on a low delay configuration. Specifically, this study includes two MPEG standard codecs (H.266/VVC VTM and JVET ECM), two AOM codecs (AV1 libaom and AVM), and two recent neural video coding models (DCVC-DC and DCVC-FM). To allow a fair and meaningful comparison, the evaluation was performed on test sequences defined in the AOM and MPEG common test conditions in the YCbCr 4:2:0 color space. The evaluation results show that the JVET ECM codecs offer the best overall coding performance among all codecs tested, with a 16.1% (based on PSNR) average BD-rate saving over AOM AVM, and 11.0% over DCVC-FM. We also observed inconsistent performance with the learned video codecs, DCVC-DC and DCVC-FM, for test content with large background motions.

Joanne Lin, Ruirui Lin, Yini Li et al.

Video instance segmentation (VIS) for low-light content remains highly challenging for both humans and machines alike, due to adverse imaging conditions including noise, blur and low-contrast. The lack of large-scale annotated datasets and the limitations of current synthetic pipelines, particularly in modeling temporal degradations, further hinder progress. Moreover, existing VIS methods are not robust to the degradations found in low-light videos and, as a result, perform poorly even when finetuned on low-light data. In this paper, we introduce \textbf{ELVIS} (\textbf{E}nhance \textbf{L}ow-light for \textbf{V}ideo \textbf{I}nstance \textbf{S}egmentation), a novel framework that enables effective domain adaptation of state-of-the-art VIS models to low-light scenarios. ELVIS comprises an unsupervised synthetic low-light video pipeline that models both spatial and temporal degradations, a calibration-free degradation profile synthesis network (VDP-Net) and an enhancement decoder head that disentangles degradations from content features. ELVIS improves performances by up to \textbf{+3.7AP} on the synthetic low-light YouTube-VIS 2019 dataset. Code will be released upon acceptance.

Zihao Qi, Chen Feng, Fan Zhang et al.

In recent years, user-generated content (UGC) has become one of the major video types consumed via streaming networks. Numerous research contributions have focused on assessing its visual quality through subjective tests and objective modeling. In most cases, objective assessments are based on a no-reference scenario, where the corresponding reference content is assumed not to be available. However, full-reference video quality assessment is also important for UGC in the delivery pipeline, particularly associated with the video transcoding process. In this context, we present a new UGC video quality database, BVI-UGC, for user-generated content transcoding, which contains 60 (non-pristine) reference videos and 1,080 test sequences. In this work, we simulated the creation of non-pristine reference sequences (with a wide range of compression distortions), typical of content uploaded to UGC platforms for transcoding. A comprehensive crowdsourced subjective study was then conducted involving more than 3,500 human participants. Based on this collected subjective data, we benchmarked the performance of 10 full-reference and 11 no-reference quality metrics. Our results demonstrate the poor performance (SROCC values are lower than 0.6) of these metrics in predicting the perceptual quality of UGC in two different scenarios (with or without a reference).

Ho Man Kwan, Tianhao Peng, Ge Gao et al.

Recent works have demonstrated the viability of utilizing over-fitted implicit neural representations (INRs) as alternatives to autoencoder-based models for neural video compression. Among these INR-based video codecs, Neural Video Representation Compression (NVRC) was the first to adopt a fully end-to-end compression framework that compresses INRs, achieving state-of-the-art performance. Moreover, some recently proposed lightweight INRs have shown comparable performance to their baseline codecs with computational complexity lower than 10kMACs/pixel. In this work, we extend NVRC toward lightweight representations, and propose NVRC-Lite, which incorporates two key changes. Firstly, we integrated multi-scale feature grids into our lightweight neural representation, and the use of higher resolution grids significantly improves the performance of INRs at low complexity. Secondly, we address the issue that existing INRs typically leverage autoregressive models for entropy coding: these are effective but impractical due to their slow coding speed. In this work, we propose an octree-based context model for entropy coding high-dimensional feature grids, which accelerates the entropy coding module of the model. Our experimental results demonstrate that NVRC-Lite outperforms C3, one of the best lightweight INR-based video codecs, with up to 21.03% and 23.06% BD-rate savings when measured in PSNR and MS-SSIM, respectively, while achieving 8.4x encoding and 2.5x decoding speedup. The implementation of NVRC-Lite will be made available.

Siyue Teng, Ge Gao, Duolikun Danier et al.

3D Gaussian Splatting (3DGS) enhances 3D scene reconstruction through explicit representation and fast rendering, demonstrating potential benefits for various low-level vision tasks, including video compression. However, existing 3DGS-based video codecs generally exhibit more noticeable visual artifacts and relatively low compression ratios. In this paper, we specifically target the perceptual enhancement of 3DGS-based video compression, based on the assumption that artifacts from 3DGS rendering and quantization resemble noisy latents sampled during diffusion training. Building on this premise, we propose a content-adaptive framework, GFix, comprising a streamlined, single-step diffusion model that serves as an off-the-shelf neural enhancer. Moreover, to increase compression efficiency, We propose a modulated LoRA scheme that freezes the low-rank decompositions and modulates the intermediate hidden states, thereby achieving efficient adaptation of the diffusion backbone with highly compressible updates. Experimental results show that GFix delivers strong perceptual quality enhancement, outperforming GSVC with up to 72.1% BD-rate savings in LPIPS and 21.4% in FID.

Qiang Zhu, Yuxuan Jiang, Shuyuan Zhu et al.

Blind video super-resolution (BVSR) is a low-level vision task which aims to generate high-resolution videos from low-resolution counterparts in unknown degradation scenarios. Existing approaches typically predict blur kernels that are spatially invariant in each video frame or even the entire video. These methods do not consider potential spatio-temporal varying degradations in videos, resulting in suboptimal BVSR performance. In this context, we propose a novel BVSR model based on Implicit Kernels, BVSR-IK, which constructs a multi-scale kernel dictionary parameterized by implicit neural representations. It also employs a newly designed recurrent Transformer to predict the coefficient weights for accurate filtering in both frame correction and feature alignment. Experimental results have demonstrated the effectiveness of the proposed BVSR-IK, when compared with four state-of-the-art BVSR models on three commonly used datasets, with BVSR-IK outperforming the second best approach, FMA-Net, by up to 0.59 dB in PSNR. Source code will be available at https://github.com/QZ1-boy/BVSR-IK.

Ge Gao, Adrian Azzarelli, Ho Man Kwan et al.

The advances in immersive technologies and 3D reconstruction have enabled the creation of digital replicas of real-world objects and environments with fine details. These processes generate vast amounts of 3D data, requiring more efficient compression methods to satisfy the memory and bandwidth constraints associated with data storage and transmission. However, the development and validation of efficient 3D data compression methods are constrained by the lack of comprehensive and high-quality volumetric video datasets, which typically require much more effort to acquire and consume increased resources compared to 2D image and video databases. To bridge this gap, we present an open multi-view volumetric human dataset, denoted BVI-CR, which contains 18 multi-view RGB-D captures and their corresponding textured polygonal meshes, depicting a range of diverse human actions. Each video sequence contains 10 views in 1080p resolution with durations between 10-15 seconds at 30FPS. Using BVI-CR, we benchmarked three conventional and neural coordinate-based multi-view video compression methods, following the MPEG MIV Common Test Conditions, and reported their rate quality performance based on various quality metrics. The results show the great potential of neural representation based methods in volumetric video compression compared to conventional video coding methods (with an up to 38\% average coding gain in PSNR). This dataset provides a development and validation platform for a variety of tasks including volumetric reconstruction, compression, and quality assessment. The database will be shared publicly at \url{https://github.com/fan-aaron-zhang/bvi-cr}.

Yuxuan Jiang, Chen Feng, Fan Zhang et al.

Knowledge distillation (KD) has emerged as a promising technique in deep learning, typically employed to enhance a compact student network through learning from their high-performance but more complex teacher variant. When applied in the context of image super-resolution, most KD approaches are modified versions of methods developed for other computer vision tasks, which are based on training strategies with a single teacher and simple loss functions. In this paper, we propose a novel Multi-Teacher Knowledge Distillation (MTKD) framework specifically for image super-resolution. It exploits the advantages of multiple teachers by combining and enhancing the outputs of these teacher models, which then guides the learning process of the compact student network. To achieve more effective learning performance, we have also developed a new wavelet-based loss function for MTKD, which can better optimize the training process by observing differences in both the spatial and frequency domains. We fully evaluate the effectiveness of the proposed method by comparing it to five commonly used KD methods for image super-resolution based on three popular network architectures. The results show that the proposed MTKD method achieves evident improvements in super-resolution performance, up to 0.46dB (based on PSNR), over state-of-the-art KD approaches across different network structures. The source code of MTKD will be made available here for public evaluation.

Yuxuan Jiang, Jakub Nawala, Fan Zhang et al.

Deep learning techniques have been applied in the context of image super-resolution (SR), achieving remarkable advances in terms of reconstruction performance. Existing techniques typically employ highly complex model structures which result in large model sizes and slow inference speeds. This often leads to high energy consumption and restricts their adoption for practical applications. To address this issue, this work employs a three-stage workflow for compressing deep SR models which significantly reduces their memory requirement. Restoration performance has been maintained through teacher-student knowledge distillation using a newly designed distillation loss. We have applied this approach to two popular image super-resolution networks, SwinIR and EDSR, to demonstrate its effectiveness. The resulting compact models, SwinIRmini and EDSRmini, attain an 89% and 96% reduction in both model size and floating-point operations (FLOPs) respectively, compared to their original versions. They also retain competitive super-resolution performance compared to their original models and other commonly used SR approaches. The source code and pre-trained models for these two lightweight SR approaches are released at https://pikapi22.github.io/CDISM/.

Ruirui Lin, Nantheera Anantrasirichai, Alexandra Malyugina et al.

Distortions caused by low-light conditions are not only visually unpleasant but also degrade the performance of computer vision tasks. The restoration and enhancement have proven to be highly beneficial. However, there are only a limited number of enhancement methods explicitly designed for videos acquired in low-light conditions. We propose a Spatio-Temporal Aligned SUNet (STA-SUNet) model using a Swin Transformer as a backbone to capture low light video features and exploit their spatio-temporal correlations. The STA-SUNet model is trained on a novel, fully registered dataset (BVI), which comprises dynamic scenes captured under varying light conditions. It is further analysed comparatively against various other models over three test datasets. The model demonstrates superior adaptivity across all datasets, obtaining the highest PSNR and SSIM values. It is particularly effective in extreme low-light conditions, yielding fairly good visualisation results.

Yuxuan Jiang, Ho Man Kwan, Tianhao Peng et al.

Recent advances in implicit neural representations (INRs) have shown significant promise in modeling visual signals for various low-vision tasks including image super-resolution (ISR). INR-based ISR methods typically learn continuous representations, providing flexibility for generating high-resolution images at any desired scale from their low-resolution counterparts. However, existing INR-based ISR methods utilize multi-layer perceptrons for parameterization in the network; this does not take account of the hierarchical structure existing in local sampling points and hence constrains the representation capability. In this paper, we propose a new \textbf{H}ierarchical encoding based \textbf{I}mplicit \textbf{I}mage \textbf{F}unction for continuous image super-resolution, \textbf{HIIF}, which leverages a novel hierarchical positional encoding that enhances the local implicit representation, enabling it to capture fine details at multiple scales. Our approach also embeds a multi-head linear attention mechanism within the implicit attention network by taking additional non-local information into account. Our experiments show that, when integrated with different backbone encoders, HIIF outperforms the state-of-the-art continuous image super-resolution methods by up to 0.17dB in PSNR. The source code of HIIF will be made publicly available at \url{www.github.com}.

Adrian Azzarelli, Nantheera Anantrasirichai, David R Bull

This paper offers the first comprehensive review of artificial intelligence (AI) research in the context of real camera content acquisition for entertainment purposes and is aimed at both researchers and cinematographers. Addressing the lack of review papers in the field of intelligent cinematography} (IC) and the breadth of related computer vision research, we present a holistic view of the IC landscape while providing technical insight, important for experts across disciplines. We provide technical background on generative AI, object detection, automated camera calibration and 3-D content acquisition, with references to assist non-technical readers. The application sections categorize work in terms of four production types: General Production, Virtual Production, Live Production and Aerial Production. Within each application section, we (1) sub-classify work according to research topic and (2) describe the trends and challenges relevant to each type of production. In the final chapter, we address the greater scope of IC research and summarize the significant potential of this area to influence the creative industries sector. We suggest that work relating to virtual production has the greatest potential to impact other mediums of production, driven by the growing interest in LED volumes/stages for in-camera virtual effects (ICVFX) and automated 3-D capture for virtual modeling of real world scenes and actors. We also address ethical and legal concerns regarding the use of creative AI that impact on artists, actors, technologists and the general public.

Ho Man Kwan, Fan Zhang, Andrew Gower et al.

Recent work on implicit neural representations (INRs) has evidenced their potential for efficiently representing and encoding conventional video content. In this paper we, for the first time, extend their application to immersive (multi-view) videos, by proposing MV-HiNeRV, a new INR-based immersive video codec. MV-HiNeRV is an enhanced version of a state-of-the-art INR-based video codec, HiNeRV, which was developed for single-view video compression. We have modified the model to learn a different group of feature grids for each view, and share the learnt network parameters among all views. This enables the model to effectively exploit the spatio-temporal and the inter-view redundancy that exists within multi-view videos. The proposed codec was used to compress multi-view texture and depth video sequences in the MPEG Immersive Video (MIV) Common Test Conditions, and tested against the MIV Test model (TMIV) that uses the VVenC video codec. The results demonstrate the superior performance of MV-HiNeRV, with significant coding gains (up to 72.33\%) over TMIV. The implementation of MV-HiNeRV is published for further development and evaluation.

Guoxi Huang, Nantheera Anantrasirichai, Fei Ye et al.

In image enhancement tasks, such as low-light and underwater image enhancement, a degraded image can correspond to multiple plausible target images due to dynamic photography conditions, such as variations in illumination. This naturally results in a one-to-many mapping challenge. To address this, we propose a Bayesian Enhancement Model (BEM) that incorporates Bayesian Neural Networks (BNNs) to capture data uncertainty and produce diverse outputs. To achieve real-time inference, we introduce a two-stage approach: Stage I employs a BNN to model the one-to-many mappings in the low-dimensional space, while Stage II refines fine-grained image details using a Deterministic Neural Network (DNN). To accelerate BNN training and convergence, we introduce a dynamic Momentum Prior. Extensive experiments on multiple low-light and underwater image enhancement benchmarks demonstrate the superiority of our method over deterministic models.

Yuxuan Jiang, Jakub Nawała, Chen Feng et al.

Super-resolution (SR) is a key technique for improving the visual quality of video content by increasing its spatial resolution while reconstructing fine details. SR has been employed in many applications including video streaming, where compressed low-resolution content is typically transmitted to end users and then reconstructed with a higher resolution and enhanced quality. To support real-time playback, it is important to implement fast SR models while preserving reconstruction quality; however most existing solutions, in particular those based on complex deep neural networks, fail to do so. To address this issue, this paper proposes a low-complexity SR method, RTSR, designed to enhance the visual quality of compressed video content, focusing on resolution up-scaling from a) 360p to 1080p and from b) 540p to 4K. The proposed approach utilizes a CNN-based network architecture, which was optimized for AV1 (SVT)-encoded content at various quantization levels based on a dual-teacher knowledge distillation method. This method was submitted to the AIM 2024 Video Super-Resolution Challenge, specifically targeting the Efficient/Mobile Real-Time Video Super-Resolution competition. It achieved the best trade-off between complexity and coding performance (measured in PSNR, SSIM and VMAF) among all six submissions. The code will be available soon.

Joanne Lin, Nantheera Anantrasirichai, David Bull

Instance segmentation for low-light imagery remains largely unexplored due to the challenges imposed by such conditions, for example shot noise due to low photon count, color distortions and reduced contrast. In this paper, we propose an end-to-end solution to address this challenging task. Our proposed method implements weighted non-local blocks (wNLB) in the feature extractor. This integration enables an inherent denoising process at the feature level. As a result, our method eliminates the need for aligned ground truth images during training, thus supporting training on real-world low-light datasets. We introduce additional learnable weights at each layer in order to enhance the network's adaptability to real-world noise characteristics, which affect different feature scales in different ways. Experimental results on several object detectors show that the proposed method outperforms the pretrained networks with an Average Precision (AP) improvement of at least +7.6, with the introduction of wNLB further enhancing AP by upto +1.3.

Yuxuan Jiang, Siyue Teng, Qiang Zhu et al.

This paper presents a general-purpose video super-resolution (VSR) method, dubbed VSR-HE, specifically designed to enhance the perceptual quality of compressed content. Targeting scenarios characterized by heavy compression, the method upscales low-resolution videos by a ratio of four, from 180p to 720p or from 270p to 1080p. VSR-HE adopts hierarchical encoding transformer blocks and has been sophisticatedly optimized to eliminate a wide range of compression artifacts commonly introduced by H.265/HEVC encoding across various quantization parameter (QP) levels. To ensure robustness and generalization, the model is trained and evaluated under diverse compression settings, allowing it to effectively restore fine-grained details and preserve visual fidelity. The proposed VSR-HE has been officially submitted to the ICME 2025 Grand Challenge on VSR for Video Conferencing (Team BVI-VSR), under both the Track 1 (General-Purpose Real-World Video Content) and Track 2 (Talking Head Videos).

Adrian Azzarelli, Ge Gao, Ho Man Kwan et al.

As research on neural volumetric video reconstruction and compression flourishes, there is a need for diverse and realistic datasets, which can be used to develop and validate reconstruction and compression models. However, existing volumetric video datasets lack diverse content in terms of both semantic and low-level features that are commonly present in real-world production pipelines. In this context, we propose a new dataset, ViVo, for VolumetrIc VideO reconstruction and compression. The dataset is faithful to real-world volumetric video production and is the first dataset to extend the definition of diversity to include both human-centric characteristics (skin, hair, etc.) and dynamic visual phenomena (transparent, reflective, liquid, etc.). Each video sequence in this database contains raw data including fourteen multi-view RGB and depth video pairs, synchronized at 30FPS with per-frame calibration and audio data, and their associated 2-D foreground masks and 3-D point clouds. To demonstrate the use of this database, we have benchmarked three state-of-the-art (SotA) 3-D reconstruction methods and two volumetric video compression algorithms. The obtained results evidence the challenging nature of the proposed dataset and the limitations of existing datasets for both volumetric video reconstruction and compression tasks, highlighting the need to develop more effective algorithms for these applications. The database and the associated results are available at https://vivo-bvicr.github.io/

Tianhao Peng, Ho Man Kwan, Yuxuan Jiang et al.

Deep learning based image Super-Resolution (ISR) relies on large training datasets to optimize model generalization; this requires substantial computational and storage resources during training. While dataset condensation has shown potential in improving data efficiency and privacy for high-level computer vision tasks, it has not yet been fully exploited for ISR. In this paper, we propose a novel Instance Data Condensation (IDC) framework specifically for ISR, which achieves instance-level data condensation through Random Local Fourier Feature Extraction and Multi-level Feature Distribution Matching. This aims to optimize feature distributions at both global and local levels and obtain high-quality synthesized training content with fine detail. This framework has been utilized to condense the most commonly used training dataset for ISR, DIV2K, with a 10% condensation rate. The resulting synthetic dataset offers comparable or (in certain cases) even better performance compared to the original full dataset and excellent training stability when used to train various popular ISR models. To the best of our knowledge, this is the first time that a condensed/synthetic dataset (with a 10% data volume) has demonstrated such performance. The source code and the synthetic dataset have been made available at https://github.com/.

Adrian Azzarelli, Nantheera Anantrasirichai, David R Bull

Novel view synthesis (NVS) has shown significant promise for applications in cinematographic production, particularly through the exploitation of Neural Radiance Fields (NeRF) and Gaussian Splatting (GS). These methods model real 3D scenes, enabling the creation of new shots that are challenging to capture in the real world due to set topology or expensive equipment requirement. This innovation also offers cinematographic advantages such as smooth camera movements, virtual re-shoots, slow-motion effects, etc. This paper explores dynamic NVS with the aim of facilitating the model selection process. We showcase its potential through a short montage filmed using various NVS models.

Guoxi Huang, Haoran Wang, Zipeng Qi et al.

Underwater image degradation poses significant challenges for 3D reconstruction, where simplified physical models often fail in complex scenes. We propose \textbf{R-Splatting}, a unified framework that bridges underwater image restoration (UIR) with 3D Gaussian Splatting (3DGS) to improve both rendering quality and geometric fidelity. Our method integrates multiple enhanced views produced by diverse UIR models into a single reconstruction pipeline. During inference, a lightweight illumination generator samples latent codes to support diverse yet coherent renderings, while a contrastive loss ensures disentangled and stable illumination representations. Furthermore, we propose \textit{Uncertainty-Aware Opacity Optimization (UAOO)}, which models opacity as a stochastic function to regularize training. This suppresses abrupt gradient responses triggered by illumination variation and mitigates overfitting to noisy or view-specific artifacts. Experiments on Seathru-NeRF and our new BlueCoral3D dataset demonstrate that R-Splatting outperforms strong baselines in both rendering quality and geometric accuracy.

Joanne Lin, Crispian Morris, Ruirui Lin et al.

Low-light conditions pose significant challenges for both human and machine annotation. This in turn has led to a lack of research into machine understanding for low-light images and (in particular) videos. A common approach is to apply annotations obtained from high quality datasets to synthetically created low light versions. In addition, these approaches are often limited through the use of unrealistic noise models. In this paper, we propose a new Degradation Estimation Network (DEN), which synthetically generates realistic standard RGB (sRGB) noise without the requirement for camera metadata. This is achieved by estimating the parameters of physics-informed noise distributions, trained in a self-supervised manner. This zero-shot approach allows our method to generate synthetic noisy content with a diverse range of realistic noise characteristics, unlike other methods which focus on recreating the noise characteristics of the training data. We evaluate our proposed synthetic pipeline using various methods trained on its synthetic data for typical low-light tasks including synthetic noise replication, video enhancement, and object detection, showing improvements of up to 24\% KLD, 21\% LPIPS, and 62\% AP$_{50-95}$, respectively.

Adrian Azzarelli, Nantheera Anantrasirichai, David R Bull

Neural Radiance Field (NeRF) research has attracted significant attention recently, with 3D modelling, virtual/augmented reality, and visual effects driving its application. While current NeRF implementations can produce high quality visual results, there is a conspicuous lack of reliable methods for evaluating them. Conventional image quality assessment methods and analytical metrics (e.g. PSNR, SSIM, LPIPS etc.) only provide approximate indicators of performance since they generalise the ability of the entire NeRF pipeline. Hence, in this paper, we propose a new test framework which isolates the neural rendering network from the NeRF pipeline and then performs a parametric evaluation by training and evaluating the NeRF on an explicit radiance field representation. We also introduce a configurable approach for generating representations specifically for evaluation purposes. This employs ray-casting to transform mesh models into explicit NeRF samples, as well as to "shade" these representations. Combining these two approaches, we demonstrate how different "tasks" (scenes with different visual effects or learning strategies) and types of networks (NeRFs and depth-wise implicit neural representations (INRs)) can be evaluated within this framework. Additionally, we propose a novel metric to measure task complexity of the framework which accounts for the visual parameters and the distribution of the spatial data. Our approach offers the potential to create a comparative objective evaluation framework for NeRF methods.

Duolikun Danier, Fan Zhang, David Bull

This paper presents a new deformable convolution-based video frame interpolation (VFI) method, using a coarse to fine 3D CNN to enhance the multi-flow prediction. This model first extracts spatio-temporal features at multiple scales using a 3D CNN, and estimates multi-flows using these features in a coarse-to-fine manner. The estimated multi-flows are then used to warp the original input frames as well as context maps, and the warped results are fused by a synthesis network to produce the final output. This VFI approach has been fully evaluated against 12 state-of-the-art VFI methods on three commonly used test databases. The results evidently show the effectiveness of the proposed method, which offers superior interpolation performance over other state of the art algorithms, with PSNR gains up to 0.19dB.

Duolikun Danier, Fan Zhang, David Bull

Video frame interpolation (VFI) is currently a very active research topic, with applications spanning computer vision, post production and video encoding. VFI can be extremely challenging, particularly in sequences containing large motions, occlusions or dynamic textures, where existing approaches fail to offer perceptually robust interpolation performance. In this context, we present a novel deep learning based VFI method, ST-MFNet, based on a Spatio-Temporal Multi-Flow architecture. ST-MFNet employs a new multi-scale multi-flow predictor to estimate many-to-one intermediate flows, which are combined with conventional one-to-one optical flows to capture both large and complex motions. In order to enhance interpolation performance for various textures, a 3D CNN is also employed to model the content dynamics over an extended temporal window. Moreover, ST-MFNet has been trained within an ST-GAN framework, which was originally developed for texture synthesis, with the aim of further improving perceptual interpolation quality. Our approach has been comprehensively evaluated -- compared with fourteen state-of-the-art VFI algorithms -- clearly demonstrating that ST-MFNet consistently outperforms these benchmarks on varied and representative test datasets, with significant gains up to 1.09dB in PSNR for cases including large motions and dynamic textures. Project page: https://danielism97.github.io/ST-MFNet.

P. R. Hill, D. R. Bull

Classification of images within the compressed domain offers significant benefits. These benefits include reduced memory and computational requirements of a classification system. This paper proposes two such methods as a proof of concept: The first classifies within the JPEG image transform domain (i.e. DCT transform data); the second classifies the JPEG compressed binary bitstream directly. These two methods are implemented using Residual Network CNNs and an adapted Vision Transformer. Top-1 accuracy of approximately 70% and 60% were achieved using these methods respectively when classifying the Caltech C101 database. Although these results are significantly behind the state of the art for classification for this database (~95%), it illustrates the first time direct bitstream image classification has been achieved. This work confirms that direct bitstream image classification is possible and could be utilised in a first pass database screening of a raw bitstream (within a wired or wireless network) or where computational, memory and bandwidth requirements are severely restricted.

P. R. Hill, D. R. Bull

Image fusion methods and metrics for their evaluation have conventionally used pixel-based or low-level features. However, for many applications, the aim of image fusion is to effectively combine the semantic content of the input images. This paper proposes a novel system for the semantic combination of visual content using pre-trained CNN network architectures. Our proposed semantic fusion is initiated through the fusion of the top layer feature map outputs (for each input image)through gradient updating of the fused image input (so-called image optimisation). Simple "choose maximum" and "local majority" filter based fusion rules are utilised for feature map fusion. This provides a simple method to combine layer outputs and thus a unique framework to fuse single-channel and colour images within a decomposition pre-trained for classification and therefore aligned with semantic fusion. Furthermore, class activation mappings of each input image are used to combine semantic information at a higher level. The developed methods are able to give equivalent low-level fusion performance to state of the art methods while providing a unique architecture to combine semantic information from multiple images.

Annika Wong, Nantheera Anantrasirichai, Thanarat H. Chalidabhongse et al.

Identification of abnormalities in red blood cells (RBC) is key to diagnosing a range of medical conditions from anaemia to liver disease. Currently this is done manually, a time-consuming and subjective process. This paper presents an automated process utilising the advantages of machine learning to increase capacity and standardisation of cell abnormality detection, and its performance is analysed. Three different machine learning technologies were used: a Support Vector Machine (SVM), a classical machine learning technology; TabNet, a deep learning architecture for tabular data; U-Net, a semantic segmentation network designed for medical image segmentation. A critical issue was the highly imbalanced nature of the dataset which impacts the efficacy of machine learning. To address this, synthesising minority class samples in feature space was investigated via Synthetic Minority Over-sampling Technique (SMOTE) and cost-sensitive learning. A combination of these two methods is investigated to improve the overall performance. These strategies were found to increase sensitivity to minority classes. The impact of unknown cells on semantic segmentation is demonstrated, with some evidence of the model applying learning of labelled cells to these anonymous cells. These findings indicate both classical models and new deep learning networks as promising methods in automating RBC abnormality detection.

Fan Zhang, Angeliki Katsenou, Christos Bampis et al.

VMAF is a machine learning based video quality assessment method, originally designed for streaming applications, which combines multiple quality metrics and video features through SVM regression. It offers higher correlation with subjective opinions compared to many conventional quality assessment methods. In this paper we propose enhancements to VMAF through the integration of new video features and alternative quality metrics (selected from a diverse pool) alongside multiple model combination. The proposed combination approach enables training on multiple databases with varying content and distortion characteristics. Our enhanced VMAF method has been evaluated on eight HD video databases, and consistently outperforms the original VMAF model (0.6.1) and other benchmark quality metrics, exhibiting higher correlation with subjective ground truth data.

Duolikun Danier, David Bull

Temporal interpolation has the potential to be a powerful tool for video compression. Existing methods for frame interpolation do not discriminate between video textures and generally invoke a single general model capable of interpolating a wide range of video content. However, past work on video texture analysis and synthesis has shown that different textures exhibit vastly different motion characteristics and they can be divided into three classes (static, dynamic continuous and dynamic discrete). In this work, we study the impact of video textures on video frame interpolation, and propose a novel framework where, given an interpolation algorithm, separate models are trained on different textures. Our study shows that video texture has significant impact on the performance of frame interpolation models and it is beneficial to have separate models specifically adapted to these texture classes, instead of training a single model that tries to learn generic motion. Our results demonstrate that models fine-tuned using our framework achieve, on average, a 0.3dB gain in PSNR on the test set used.

N. Anantrasirichai, David Bull

Low-light image sequences generally suffer from spatio-temporal incoherent noise, flicker and blurring of moving objects. These artefacts significantly reduce visual quality and, in most cases, post-processing is needed in order to generate acceptable quality. Most state-of-the-art enhancement methods based on machine learning require ground truth data but this is not usually available for naturally captured low light sequences. We tackle these problems with an unpaired-learning method that offers simultaneous colorization and denoising. Our approach is an adaptation of the CycleGAN structure. To overcome the excessive memory limitations associated with ultra high resolution content, we propose a multiscale patch-based framework, capturing both local and contextual features. Additionally, an adaptive temporal smoothing technique is employed to remove flickering artefacts. Experimental results show that our method outperforms existing approaches in terms of subjective quality and that it is robust to variations in brightness levels and noise.

Di Ma, Fan Zhang, David R. Bull

We propose a new Generative Adversarial Network for Compressed Video quality Enhancement (CVEGAN). The CVEGAN generator benefits from the use of a novel Mul2Res block (with multiple levels of residual learning branches), an enhanced residual non-local block (ERNB) and an enhanced convolutional block attention module (ECBAM). The ERNB has also been employed in the discriminator to improve the representational capability. The training strategy has also been re-designed specifically for video compression applications, to employ a relativistic sphere GAN (ReSphereGAN) training methodology together with new perceptual loss functions. The proposed network has been fully evaluated in the context of two typical video compression enhancement tools: post-processing (PP) and spatial resolution adaptation (SRA). CVEGAN has been fully integrated into the MPEG HEVC video coding test model (HM16.20) and experimental results demonstrate significant coding gains (up to 28% for PP and 38% for SRA compared to the anchor) over existing state-of-the-art architectures for both coding tools across multiple datasets.

Fan Zhang, David Hall, Tao Xu et al.

In this paper, we present a workflow for the simulation of drone operations exploiting realistic background environments constructed within Unreal Engine 4 (UE4). Methods for environmental image capture, 3D reconstruction (photogrammetry) and the creation of foreground assets are presented along with a flexible and user-friendly simulation interface. Given the geographical location of the selected area and the camera parameters employed, the scanning strategy and its associated flight parameters are first determined for image capture. Source imagery can be extracted from virtual globe software or obtained through aerial photography of the scene (e.g. using drones). The latter case is clearly more time consuming but can provide enhanced detail, particularly where coverage of virtual globe software is limited. The captured images are then used to generate 3D background environment models employing photogrammetry software. The reconstructed 3D models are then imported into the simulation interface as background environment assets together with appropriate foreground object models as a basis for shot planning and rehearsal. The tool supports both free-flight and parameterisable standard shot types along with programmable scenarios associated with foreground assets and event dynamics. It also supports the exporting of flight plans. Camera shots can also be designed to provide suitable coverage of any landmarks which need to appear in-shot. This simulation tool will contribute to enhanced productivity, improved safety (awareness and mitigations for crowds and buildings), improved confidence of operators and directors and ultimately enhanced quality of viewer experience.

Fan Zhang, Di Ma, Chen Feng et al.

In recent years, video compression techniques have been significantly challenged by the rapidly increased demands associated with high quality and immersive video content. Among various compression tools, post-processing can be applied on reconstructed video content to mitigate visible compression artefacts and to enhance overall perceptual quality. Inspired by advances in deep learning, we propose a new CNN-based post-processing approach, which has been integrated with two state-of-the-art coding standards, VVC and AV1. The results show consistent coding gains on all tested sequences at various spatial resolutions, with average bit rate savings of 4.0% and 5.8% against original VVC and AV1 respectively (based on the assessment of PSNR). This network has also been trained with perceptually inspired loss functions, which have further improved reconstruction quality based on perceptual quality assessment (VMAF), with average coding gains of 13.9% over VVC and 10.5% against AV1.

Di Ma, Fan Zhang, David R. Bull

In this paper, we propose a novel convolutional neural network (CNN) architecture, MFRNet, for post-processing (PP) and in-loop filtering (ILF) in the context of video compression. This network consists of four Multi-level Feature review Residual dense Blocks (MFRBs), which are connected using a cascading structure. Each MFRB extracts features from multiple convolutional layers using dense connections and a multi-level residual learning structure. In order to further improve information flow between these blocks, each of them also reuses high dimensional features from the previous MFRB. This network has been integrated into PP and ILF coding modules for both HEVC (HM 16.20) and VVC (VTM 7.0), and fully evaluated under the JVET Common Test Conditions using the Random Access configuration. The experimental results show significant and consistent coding gains over both anchor codecs (HEVC HM and VVC VTM) and also over other existing CNN-based PP/ILF approaches based on Bjontegaard Delta measurements using both PSNR and VMAF for quality assessment. When MFRNet is integrated into HM 16.20, gains up to 16.0% (BD-rate VMAF) are demonstrated for ILF, and up to 21.0% (BD-rate VMAF) for PP. The respective gains for VTM 7.0 are up to 5.1% for ILF and up to 7.1% for PP.

Nantheera Anantrasirichai, Juliet Biggs, Krisztina Kelevitz et al.

The large volumes of Sentinel-1 data produced over Europe are being used to develop pan-national ground motion services. However, simple analysis techniques like thresholding cannot detect and classify complex deformation signals reliably making providing usable information to a broad range of non-expert stakeholders a challenge. Here we explore the applicability of deep learning approaches by adapting a pre-trained convolutional neural network (CNN) to detect deformation in a national-scale velocity field. For our proof-of-concept, we focus on the UK where previously identified deformation is associated with coal-mining, ground water withdrawal, landslides and tunnelling. The sparsity of measurement points and the presence of spike noise make this a challenging application for deep learning networks, which involve calculations of the spatial convolution between images. Moreover, insufficient ground truth data exists to construct a balanced training data set, and the deformation signals are slower and more localised than in previous applications. We propose three enhancement methods to tackle these problems: i) spatial interpolation with modified matrix completion, ii) a synthetic training dataset based on the characteristics of real UK velocity map, and iii) enhanced over-wrapping techniques. Using velocity maps spanning 2015-2019, our framework detects several areas of coal mining subsidence, uplift due to dewatering, slate quarries, landslides and tunnel engineering works. The results demonstrate the potential applicability of the proposed framework to the development of automated ground motion analysis systems.

Nantheera Anantrasirichai, Majid Geravand, David Braendler et al.

Disparity/depth estimation from sequences of stereo images is an important element in 3D vision. Owing to occlusions, imperfect settings and homogeneous luminance, accurate estimate of depth remains a challenging problem. Targetting view synthesis, we propose a novel learning-based framework making use of dilated convolution, densely connected convolutional modules, compact decoder and skip connections. The network is shallow but dense, so it is fast and accurate. Two additional contributions -- a non-linear adjustment of the depth resolution and the introduction of a projection loss, lead to reduction of estimation error by up to 20% and 25% respectively. The results show that our network outperforms state-of-the-art methods with an average improvement in accuracy of depth estimation and view synthesis by approximately 45% and 34% respectively. Where our method generates comparable quality of estimated depth, it performs 10 times faster than those methods.

Jing Gao, N. Anantrasirichai, David Bull

This paper describes a novel deep learning-based method for mitigating the effects of atmospheric distortion. We have built an end-to-end supervised convolutional neural network (CNN) to reconstruct turbulence-corrupted video sequence. Our framework has been developed on the residual learning concept, where the spatio-temporal distortions are learnt and predicted. Our experiments demonstrate that the proposed method can deblur, remove ripple effect and enhance contrast of the video sequences simultaneously. Our model was trained and tested with both simulated and real distortions. Experimental results of the real distortions show that our method outperforms the existing ones by up to 3.8% in term of the quality of restored images, and it achieves faster speed than the state-of-the-art methods by up to 23 times with GPU implementation.

P. R. Hill, A. Kumar, M. Temimi et al.

This paper describes the application of machine learning techniques to develop a state-of-the-art detection and prediction system for spatiotemporal events found within remote sensing data; specifically, Harmful Algal Bloom events (HABs). We propose an HAB detection system based on: a ground truth historical record of HAB events, a novel spatiotemporal datacube representation of each event (from MODIS and GEBCO bathymetry data) and a variety of machine learning architectures utilising state-of-the-art spatial and temporal analysis methods based on Convolutional Neural Networks (CNNs), Long Short-Term Memory (LSTM) components together with Random Forest and Support Vector Machine (SVM) classification methods. This work has focused specifically on the case study of the detection of Karenia Brevis Algae (K. brevis) HAB events within the coastal waters of Florida (over 2850 events from 2003 to 2018; an order of magnitude larger than any previous machine learning detection study into HAB events). The development of multimodal spatiotemporal datacube data structures and associated novel machine learning methods give a unique architecture for the automatic detection of environmental events. Specifically, when applied to the detection of HAB events it gives a maximum detection accuracy of 91% and a Kappa coefficient of 0.81 for the Florida data considered. A HAB forecast system was also developed where a temporal subset of each datacube was used to predict the presence of a HAB in the future. This system was not significantly less accurate than the detection system being able to predict with 86% accuracy up to 8 days in the future.

Fan Zhang, Mariana Afonso, David R. Bull

We present a new video compression framework (ViSTRA2) which exploits adaptation of spatial resolution and effective bit depth, down-sampling these parameters at the encoder based on perceptual criteria, and up-sampling at the decoder using a deep convolution neural network. ViSTRA2 has been integrated with the reference software of both the HEVC (HM 16.20) and VVC (VTM 4.01), and evaluated under the Joint Video Exploration Team Common Test Conditions using the Random Access configuration. Our results show consistent and significant compression gains against HM and VVC based on Bjønegaard Delta measurements, with average BD-rate savings of 12.6% (PSNR) and 19.5% (VMAF) over HM and 5.5% (PSNR) and 8.6% (VMAF) over VTM.