David Bull
YOU?
Author Swipe
View article: CAMP-VQA: Caption-Embedded Multimodal Perception for No-Reference Quality Assessment of Compressed Video
CAMP-VQA: Caption-Embedded Multimodal Perception for No-Reference Quality Assessment of Compressed Video Open
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-pr…
View article: Towards a General-Purpose Zero-Shot Synthetic Low-Light Image and Video Pipeline
Towards a General-Purpose Zero-Shot Synthetic Low-Light Image and Video Pipeline Open
View article: From Restoration to Reconstruction: Rethinking 3D Gaussian Splatting for Underwater Scenes
From Restoration to Reconstruction: Rethinking 3D Gaussian Splatting for Underwater Scenes Open
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 …
View article: Compressed Video Super-Resolution based on Hierarchical Encoding
Compressed Video Super-Resolution based on Hierarchical Encoding Open
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 ups…
View article: Instance Data Condensation for Image Super-Resolution
Instance Data Condensation for Image Super-Resolution Open
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 potent…
View article: Towards a General-Purpose Zero-Shot Synthetic Low-Light Image and Video Pipeline
Towards a General-Purpose Zero-Shot Synthetic Low-Light Image and Video Pipeline Open
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 an…
View article: Wavelet-Based Topological Loss for Low-Light Image Denoising
Wavelet-Based Topological Loss for Low-Light Image Denoising Open
Despite significant advances in image denoising, most algorithms rely on supervised learning, with their performance largely dependent on the quality and diversity of training data. It is widely assumed that digital image distortions are c…
View article: Blind Video Super-Resolution based on Implicit Kernels
Blind Video Super-Resolution based on Implicit Kernels Open
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 spa…
View article: Deep learning techniques for atmospheric turbulence removal: a review
Deep learning techniques for atmospheric turbulence removal: a review Open
Atmospheric turbulence significantly complicates the interpretation and analysis of images by distorting them, making it hard to classify and track objects within a scene using traditional methods. This distortion arises from unpredictable…
View article: Intelligent Cinematography: a review of AI research for cinematographic production
Intelligent Cinematography: a review of AI research for cinematographic production Open
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 la…
View article: Bayesian Neural Networks for One-to-Many Mapping in Image Enhancement
Bayesian Neural Networks for One-to-Many Mapping in Image Enhancement Open
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. This naturally results in a one-to-many mapping prob…
View article: Exploring Dynamic Novel View Synthesis Technologies for Cinematography
Exploring Dynamic Novel View Synthesis Technologies for Cinematography Open
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…
View article: Benchmarking Conventional and Learned Video Codecs with a Low-Delay Configuration
Benchmarking Conventional and Learned Video Codecs with a Low-Delay Configuration Open
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 cert…
View article: HIIF: Hierarchical Encoding based Implicit Image Function for Continuous Super-resolution
HIIF: Hierarchical Encoding based Implicit Image Function for Continuous Super-resolution Open
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 repre…
View article: RTSR: A Real-Time Super-Resolution Model for AV1 Compressed Content
RTSR: A Real-Time Super-Resolution Model for AV1 Compressed Content Open
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 c…
View article: BVI-CR: A Multi-View Human Dataset for Volumetric Video Compression
BVI-CR: A Multi-View Human Dataset for Volumetric Video Compression Open
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…
View article: Narrative predicts cardiac synchrony in audiences
Narrative predicts cardiac synchrony in audiences Open
View article: UW-GS: Distractor-Aware 3D Gaussian Splatting for Enhanced Underwater Scene Reconstruction
UW-GS: Distractor-Aware 3D Gaussian Splatting for Enhanced Underwater Scene Reconstruction Open
3D Gaussian splatting (3DGS) offers the capability to achieve real-time high quality 3D scene rendering. However, 3DGS assumes that the scene is in a clear medium environment and struggles to generate satisfactory representations in underw…
View article: Rate-Quality or Energy-Quality Pareto Fronts for Adaptive Video Streaming?
Rate-Quality or Energy-Quality Pareto Fronts for Adaptive Video Streaming? Open
View article: NVRC: Neural Video Representation Compression
NVRC: Neural Video Representation Compression Open
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 vi…
View article: Deep Learning Techniques for Atmospheric Turbulence Removal: A Review
Deep Learning Techniques for Atmospheric Turbulence Removal: A Review Open
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 …
View article: BVI-UGC: A Video Quality Database for User-Generated Content Transcoding
BVI-UGC: A Video Quality Database for User-Generated Content Transcoding Open
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 mode…
View article: BVI-AOM: A New Training Dataset for Deep Video Compression Optimization
BVI-AOM: A New Training Dataset for Deep Video Compression Optimization Open
Deep learning is now playing an important role in enhancing the performance of conventional hybrid video codecs. These learning-based methods typically require diverse and representative training material for optimization in order to achie…
View article: ReLaX-VQA: Residual Fragment and Layer Stack Extraction for Enhancing Video Quality Assessment
ReLaX-VQA: Residual Fragment and Layer Stack Extraction for Enhancing Video Quality Assessment Open
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 …
View article: BVI-RLV: A Fully Registered Dataset and Benchmarks for Low-Light Video Enhancement
BVI-RLV: A Fully Registered Dataset and Benchmarks for Low-Light Video Enhancement Open
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 da…
View article: MVAD: A Multiple Visual Artifact Detector for Video Streaming
MVAD: A Multiple Visual Artifact Detector for Video Streaming Open
Visual artifacts are often introduced into streamed video content, due to prevailing conditions during content production and delivery. Since these can degrade the quality of the user's experience, it is important to automatically and accu…
View article: RMT-BVQA: Recurrent Memory Transformer-based Blind Video Quality Assessment for Enhanced Video Content
RMT-BVQA: Recurrent Memory Transformer-based Blind Video Quality Assessment for Enhanced Video Content Open
With recent advances in deep learning, numerous algorithms have been developed to enhance video quality, reduce visual artifacts, and improve perceptual quality. However, little research has been reported on the quality assessment of enhan…
View article: Reviewing Intelligent Cinematography: AI research for camera-based video production
Reviewing Intelligent Cinematography: AI research for camera-based video production Open
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 la…
View article: CVEGAN: A perceptually-inspired GAN for Compressed Video Enhancement
CVEGAN: A perceptually-inspired GAN for Compressed Video Enhancement Open
We propose a new Generative Adversarial Network for Compressed Video frame quality Enhancement (CVEGAN). The CVEGAN generator benefits from the use of a novel Mul2Res block (with multiple levels of residual learning branches), an enhanced …
View article: MTKD: Multi-Teacher Knowledge Distillation for Image Super-Resolution
MTKD: Multi-Teacher Knowledge Distillation for Image Super-Resolution Open
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 c…