Thomas Bashford-Rogers
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Thomas Bashford-Rogers has a total of 43 co-authors. Here are the top co-authors by number of shared publications:
- Kurt Debattista
WMG, University of Warwick, Coventry, U.K.
18 shared publications - Alan Chalmers
WMG, University of Warwick, Coventry, UK
4 shared publications - Jingchao Peng
School of Information Science and Engineering, East China University of Science and Technology, Shanghai, China
4 shared publications Alan Chalmers
Warwick Manufacturing Group, The University of Warwick, Coventry, U.K.
3 shared publications- Haitao Zhao
School of Information Science and Engineering, East China University of Science and Technology, Shanghai, China
3 shared publications - Luís Paulo Santos
International Iberian Nanotechnology Laboratory (INL), Braga, Portugal
3 shared publications
Latest Publications
- 9 February 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Artificial Intelligence
- Vol. PP (8) , 1-13
Luminance Component Analysis for Exposure Correction
Exposure correction methods aim to adjust the luminance while maintaining other luminance-unrelated information. However, current exposure correction methods have difficulty in fully separating luminance-related and luminanceunrelated components, leading to distortions in color, loss of detail, and requiring extra restoration procedures. Inspired by principal component analysis (PCA), this paper proposes an exposure correction method called luminance component analysis (LCA). LCA applies the orthogonal constraint to a U-Net structure to decouple luminance-related and luminanceunrelated features. With decoupled luminance-related features, LCA adjusts only the luminance-related components while keeping the luminance-unrelated components unchanged. To optimize the orthogonal constraint problem, LCA employs a geometric optimization algorithm, which converts the constrained problem in Euclidean space to an unconstrained problem in orthogonal Stiefel manifolds. Extensive experiments show that LCA can decouple the luminance feature from the RGB color space. Moreover, LCA achieves the best PSNR (21.33) and SSIM (0.88) in the exposure correction dataset with 28.72 FPS.
- 9 February 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Artificial Intelligence
- Vol. PP (8) , 1-13
Luminance Component Analysis for Exposure Correction
Exposure correction methods aim to adjust the luminance while maintaining other luminance-unrelated information. However, current exposure correction methods have difficulty in fully separating luminance-related and luminanceunrelated components, leading to distortions in color, loss of detail, and requiring extra restoration procedures. Inspired by principal component analysis (PCA), this paper proposes an exposure correction method called luminance component analysis (LCA). LCA applies the orthogonal constraint to a U-Net structure to decouple luminance-related and luminanceunrelated features. With decoupled luminance-related features, LCA adjusts only the luminance-related components while keeping the luminance-unrelated components unchanged. To optimize the orthogonal constraint problem, LCA employs a geometric optimization algorithm, which converts the constrained problem in Euclidean space to an unconstrained problem in orthogonal Stiefel manifolds. Extensive experiments show that LCA can decouple the luminance feature from the RGB color space. Moreover, LCA achieves the best PSNR (21.33) and SSIM (0.88) in the exposure correction dataset with 28.72 FPS.
- 6 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Multimedia
- Vol. 28 (15209210) , 2865-2875
CapHDR2IR: Caption-Driven Transfer From Visible Light to Infrared Domain
Infrared (IR) imaging offers advantages in several fields due to its unique ability of capturing content in extreme light conditions. However, the demanding hardware requirements of high-resolution IR sensors limit its widespread application. As an alternative, visible light can be used to synthesize IR images but this causes a loss of fidelity in image details and introduces inconsistencies due to lack of contextual awareness of the scene. This stems from a combination of using visible light with a standard dynamic range, especially under extreme lighting, and a lack of contextual awareness can result in pseudo-thermal-crossover artifacts. This occurs when multiple objects with similar temperatures appear indistinguishable in the training data, further exacerbating the loss of fidelity. To solve this challenge, this paper proposes CapHDR2IR, a novel framework incorporating vision-language models using high dynamic range (HDR) images as inputs to generate IR images. HDR images capture a wider range of luminance variations, ensuring reliable IR image generation in different light conditions. Additionally, a dense caption branch integrates semantic understanding, resulting in more meaningful and discernible IR outputs. Extensive experiments on the HDRT dataset show that the proposed CapHDR2IR achieves state-of-the-art performance compared with existing general domain transfer methods and those tailored for visible-to-infrared image translation. The source code is available at https://github.com/PengJingchao/CapHDR2IR.
- 6 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Multimedia
- Vol. 28 (15209210) , 2865-2875
CapHDR2IR: Caption-Driven Transfer From Visible Light to Infrared Domain
Infrared (IR) imaging offers advantages in several fields due to its unique ability of capturing content in extreme light conditions. However, the demanding hardware requirements of high-resolution IR sensors limit its widespread application. As an alternative, visible light can be used to synthesize IR images but this causes a loss of fidelity in image details and introduces inconsistencies due to lack of contextual awareness of the scene. This stems from a combination of using visible light with a standard dynamic range, especially under extreme lighting, and a lack of contextual awareness can result in pseudo-thermal-crossover artifacts. This occurs when multiple objects with similar temperatures appear indistinguishable in the training data, further exacerbating the loss of fidelity. To solve this challenge, this paper proposes CapHDR2IR, a novel framework incorporating vision-language models using high dynamic range (HDR) images as inputs to generate IR images. HDR images capture a wider range of luminance variations, ensuring reliable IR image generation in different light conditions. Additionally, a dense caption branch integrates semantic understanding, resulting in more meaningful and discernible IR outputs. Extensive experiments on the HDRT dataset show that the proposed CapHDR2IR achieves state-of-the-art performance compared with existing general domain transfer methods and those tailored for visible-to-infrared image translation. The source code is available at https://github.com/PengJingchao/CapHDR2IR.
- 10 December 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Visualization and Computer Graphics
- Vol. 32 (2) , 1743-1753
Image Based Whole Sky Cloud Volume Generation
Accurate illumination is crucial for many imaging and vision applications, and skies are the dominant source of lighting in many scenes. Most existing work for representing sky illumination has focused on clear skies or more recently generative approaches for synthesizing clouds. However, these are very limited in that they assume distant illumination and do not capture the 3D properties of clouds. This paper presents a novel and principled approach to extract 3D whole-sky volumetric representations of clouds which can be used for imaging applications. Our approach extracts clouds from a single fisheye capture of the sky via an iterative optimization process. We achieve this by exploiting the physical properties of light scattering in clouds and use these to drive a domain-specific light transport simulation algorithm to render the images required for optimization. Results for this method provide high accuracy when re-rendering with our reconstructed clouds compared to real captures, and also enable novel uses of environment maps such as inclusion of captured clouds in renderings, cloud shadows, and more accurate aerial perspective and lighting.
- 10 December 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Visualization and Computer Graphics
- Vol. 32 (2) , 1743-1753
Image Based Whole Sky Cloud Volume Generation
Accurate illumination is crucial for many imaging and vision applications, and skies are the dominant source of lighting in many scenes. Most existing work for representing sky illumination has focused on clear skies or more recently generative approaches for synthesizing clouds. However, these are very limited in that they assume distant illumination and do not capture the 3D properties of clouds. This paper presents a novel and principled approach to extract 3D whole-sky volumetric representations of clouds which can be used for imaging applications. Our approach extracts clouds from a single fisheye capture of the sky via an iterative optimization process. We achieve this by exploiting the physical properties of light scattering in clouds and use these to drive a domain-specific light transport simulation algorithm to render the images required for optimization. Results for this method provide high accuracy when re-rendering with our reconstructed clouds compared to real captures, and also enable novel uses of environment maps such as inclusion of captured clouds in renderings, cloud shadows, and more accurate aerial perspective and lighting.
- 6 November 2025
- Published by Elsevier in Information Fusion
- Vol. 127
Balancing light and shadow: Multi-modal image exposure restoration via frequency-phase-driven RGB-IR integration
- 6 November 2025
- Published by Elsevier in Information Fusion
- Vol. 127
Balancing light and shadow: Multi-modal image exposure restoration via frequency-phase-driven RGB-IR integration
- 19 March 2025
- Published by Elsevier in Information Fusion
- Vol. 120
HDRT: A large-scale dataset for infrared-guided HDR imaging
- 19 March 2025
- Published by Elsevier in Information Fusion
- Vol. 120
HDRT: A large-scale dataset for infrared-guided HDR imaging
- Open Access
- 27 November 2024
- Published by Elsevier in Computers & Graphics
- Vol. 126
A multi-timescale image space model for dynamic cloud illumination
- 27 November 2024
- Published by Elsevier in Computers & Graphics
- Vol. 126
Open AccessA multi-timescale image space model for dynamic cloud illumination
- 8 April 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Visualization and Computer Graphics
- Vol. 31 (4) , 2223-2234
Towards Quantum Ray Tracing
Rendering on conventional computers is capable of generating realistic imagery, but the computational complexity of these light transport algorithms is a limiting factor of image synthesis. Quantum computers have the potential to significantly improve rendering performance through reducing the underlying complexity of the algorithms behind light transport. This paper investigates hybrid quantum-classical algorithms for ray tracing, a core component of most rendering techniques. Through a practical implementation of quantum ray tracing in a 3D environment, we show quantum approaches provide a quadratic improvement in query complexity compared to the equivalent classical approach. Based on domain specific knowledge, we then propose algorithms to significantly reduce the computation required for quantum ray tracing through exploiting image space coherence and a principled termination criteria for quantum searching. We show results obtained using a simulator for both Whitted style ray tracing, and for accelerating ray tracing operations when performing classical Monte Carlo integration for area lights and indirect illumination.
- 8 April 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Visualization and Computer Graphics
- Vol. 31 (4) , 2223-2234
Towards Quantum Ray Tracing
Rendering on conventional computers is capable of generating realistic imagery, but the computational complexity of these light transport algorithms is a limiting factor of image synthesis. Quantum computers have the potential to significantly improve rendering performance through reducing the underlying complexity of the algorithms behind light transport. This paper investigates hybrid quantum-classical algorithms for ray tracing, a core component of most rendering techniques. Through a practical implementation of quantum ray tracing in a 3D environment, we show quantum approaches provide a quadratic improvement in query complexity compared to the equivalent classical approach. Based on domain specific knowledge, we then propose algorithms to significantly reduce the computation required for quantum ray tracing through exploiting image space coherence and a principled termination criteria for quantum searching. We show results obtained using a simulator for both Whitted style ray tracing, and for accelerating ray tracing operations when performing classical Monte Carlo integration for area lights and indirect illumination.
- Open Access
- 23 March 2024
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Graphics
- Vol. 43 (2) , 1-16
Self-supervised High Dynamic Range Imaging: What Can Be Learned from a Single 8-bit Video?
Recently, Deep Learning-based methods for inverse tone mapping standard dynamic range (SDR) images to obtain high dynamic range (HDR) images have become very popular. These methods manage to fill over-exposed areas convincingly both in terms of details and dynamic range. To be effective, deep learning-based methods need to learn from large datasets and transfer this knowledge to the network weights. In this work, we tackle this problem from a completely different perspective. What can we learn from a single SDR 8-bit video? With the presented self-supervised approach, we show that, in many cases, a single SDR video is sufficient to generate an HDR video of the same quality or better than other state-of-the-art methods.
- 23 March 2024
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Graphics
- Vol. 43 (2) , 1-16
Open AccessSelf-supervised High Dynamic Range Imaging: What Can Be Learned from a Single 8-bit Video?
Recently, Deep Learning-based methods for inverse tone mapping standard dynamic range (SDR) images to obtain high dynamic range (HDR) images have become very popular. These methods manage to fill over-exposed areas convincingly both in terms of details and dynamic range. To be effective, deep learning-based methods need to learn from large datasets and transfer this knowledge to the network weights. In this work, we tackle this problem from a completely different perspective. What can we learn from a single SDR 8-bit video? With the presented self-supervised approach, we show that, in many cases, a single SDR video is sufficient to generate an HDR video of the same quality or better than other state-of-the-art methods.
- Open Access
- 10 December 2023
- Published by Association for Computing Machinery (ACM)
- p. 1-11
Conditional Resampled Importance Sampling and ReSTIR
Recent work on generalized resampled importance sampling (GRIS) enables importance-sampled Monte Carlo integration with random variable weights replacing the usual division by probability density. This enables very flexible spatiotemporal sample reuse, even if neighboring samples (e.g., light paths) have intractable probability densities. Unlike typical Monte Carlo integration, which samples according to some PDF, GRIS instead resamples existing samples. But resampling with GRIS assumes samples have tractable marginal contribution weights, which is problematic if reusing, for example, light subpaths from unidirectionally-sampled paths. Reusing such subpaths requires conditioning by (non-reused) segments of the path prefixes. In this paper, we extend GRIS to conditional probability spaces, showing correctness given certain conditional independence between integration variables and their unbiased contribution weights. We show proper conditioning when using GRIS over randomized conditional domains and how to formulate a joint unbiased contribution weight for unbiased integration. To show our theory has practical impact, we prototype a modified ReSTIR PT with a final gather pass. This reuses subpaths, postponing reuse at least one bounce along each light path. As in photon mapping, such a final gather reduces blotchy artifacts from sample correlation and reduced correlation improves the behavior of modern denoisers on ReSTIR PT signals.
- 10 December 2023
- Published by Association for Computing Machinery (ACM)
- p. 1-11
Open AccessConditional Resampled Importance Sampling and ReSTIR
Recent work on generalized resampled importance sampling (GRIS) enables importance-sampled Monte Carlo integration with random variable weights replacing the usual division by probability density. This enables very flexible spatiotemporal sample reuse, even if neighboring samples (e.g., light paths) have intractable probability densities. Unlike typical Monte Carlo integration, which samples according to some PDF, GRIS instead resamples existing samples. But resampling with GRIS assumes samples have tractable marginal contribution weights, which is problematic if reusing, for example, light subpaths from unidirectionally-sampled paths. Reusing such subpaths requires conditioning by (non-reused) segments of the path prefixes. In this paper, we extend GRIS to conditional probability spaces, showing correctness given certain conditional independence between integration variables and their unbiased contribution weights. We show proper conditioning when using GRIS over randomized conditional domains and how to formulate a joint unbiased contribution weight for unbiased integration. To show our theory has practical impact, we prototype a modified ReSTIR PT with a final gather pass. This reuses subpaths, postponing reuse at least one bounce along each light path. As in photon mapping, such a final gather reduces blotchy artifacts from sample correlation and reduced correlation improves the behavior of modern denoisers on ReSTIR PT signals.
- 14 November 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Industrial Informatics
- Vol. 20 (3) , 4816-4827
Generating Synthetic Training Images to Detect Split Defects in Stamped Components
Detecting rare and costly defects, such as necks and splits in sheet metal stamping, remains challenging for deep learning models due to low failure rates entailing few available samples to train on. Synthetic images provide a simulated alternative; however, the two main current approaches have limitations for generating split defect images. Image synthesis-based models generate implausible training data, while physics-based models are computationally expensive and lack the diversity required. To address this, we present a novel method combining the advantages of physics-based simulation with synthetic-based defect generation. The method first generates deformed 3-D geometry through finite element simulation with plausible split locations determined using a forming limit curve. Subsequently, the fine details of captured real splits are mapped to the identified locations to generate realistic defect features. Our results show that training a deep neural network with the addition of synthetic images improves the performance significantly.
- 14 November 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Industrial Informatics
- Vol. 20 (3) , 4816-4827
Generating Synthetic Training Images to Detect Split Defects in Stamped Components
Detecting rare and costly defects, such as necks and splits in sheet metal stamping, remains challenging for deep learning models due to low failure rates entailing few available samples to train on. Synthetic images provide a simulated alternative; however, the two main current approaches have limitations for generating split defect images. Image synthesis-based models generate implausible training data, while physics-based models are computationally expensive and lack the diversity required. To address this, we present a novel method combining the advantages of physics-based simulation with synthetic-based defect generation. The method first generates deformed 3-D geometry through finite element simulation with plausible split locations determined using a forming limit curve. Subsequently, the fine details of captured real splits are mapped to the identified locations to generate realistic defect features. Our results show that training a deep neural network with the addition of synthetic images improves the performance significantly.