Rafał Mantiuk

Rafal K. Mantiuk, Dounia Hammou, Param Hanji · cambridge

High-Dynamic-Range Visual-Difference-Predictor version 3, or HDR-VDP-3, is a visual metric that can fulfill several tasks, such as full-reference image/video quality assessment, prediction of visual differences between a pair of images, or prediction of contrast distortions. Here we present a high-level overview of the metric, position it with respect to related work, explain the main differences compared to version 2.2, and describe how the metric was adapted for the HDR Video Quality Measurement Grand Challenge 2023.

Hanxue Liang, Tianhao Wu, Param Hanji et al. · cambridge

Neural view synthesis (NVS) is one of the most successful techniques for synthesizing free viewpoint videos, capable of achieving high fidelity from only a sparse set of captured images. This success has led to many variants of the techniques, each evaluated on a set of test views typically using image quality metrics such as PSNR, SSIM, or LPIPS. There has been a lack of research on how NVS methods perform with respect to perceived video quality. We present the first study on perceptual evaluation of NVS and NeRF variants. For this study, we collected two datasets of scenes captured in a controlled lab environment as well as in-the-wild. In contrast to existing datasets, these scenes come with reference video sequences, allowing us to test for temporal artifacts and subtle distortions that are easily overlooked when viewing only static images. We measured the quality of videos synthesized by several NVS methods in a well-controlled perceptual quality assessment experiment as well as with many existing state-of-the-art image/video quality metrics. We present a detailed analysis of the results and recommendations for dataset and metric selection for NVS evaluation.

Aamir Mustafa, Param Hanji, Rafal K. Mantiuk · cambridge

Many image enhancement or editing operations, such as forward and inverse tone mapping or color grading, do not have a unique solution, but instead a range of solutions, each representing a different style. Despite this, existing learning-based methods attempt to learn a unique mapping, disregarding this style. In this work, we show that information about the style can be distilled from collections of image pairs and encoded into a 2- or 3-dimensional vector. This gives us not only an efficient representation but also an interpretable latent space for editing the image style. We represent the global color mapping between a pair of images as a custom normalizing flow, conditioned on a polynomial basis of the pixel color. We show that such a network is more effective than PCA or VAE at encoding image style in low-dimensional space and lets us obtain an accuracy close to 40 dB, which is about 7-10 dB improvement over the state-of-the-art methods.

Param Hanji, Rafał K. Mantiuk · cambridge

Merging multi-exposure image stacks into a high dynamic range (HDR) image requires knowledge of accurate exposure times. When exposure times are inaccurate, for example, when they are extracted from a camera's EXIF metadata, the reconstructed HDR images reveal banding artifacts at smooth gradients. To remedy this, we propose to estimate exposure ratios directly from the input images. We derive the exposure time estimation as an optimization problem, in which pixels are selected from pairs of exposures to minimize estimation error caused by camera noise. When pixel values are represented in the logarithmic domain, the problem can be solved efficiently using a linear solver. We demonstrate that the estimation can be easily made robust to pixel misalignment caused by camera or object motion by collecting pixels from multiple spatial tiles. The proposed automatic exposure estimation and alignment eliminates banding artifacts in popular datasets and is essential for applications that require physically accurate reconstructions, such as measuring the modulation transfer function of a display. The code for the method is available.

Peibei Cao, Rafal K. Mantiuk, Kede Ma

High dynamic range (HDR) rendering has the ability to faithfully reproduce the wide luminance ranges in natural scenes, but how to accurately assess the rendering quality is relatively underexplored. Existing quality models are mostly designed for low dynamic range (LDR) images, and do not align well with human perception of HDR image quality. To fill this gap, we propose a family of HDR quality metrics, in which the key step is employing a simple inverse display model to decompose an HDR image into a stack of LDR images with varying exposures. Subsequently, these decomposed images are assessed through well-established LDR quality metrics. Our HDR quality models present three distinct benefits. First, they directly inherit the recent advancements of LDR quality metrics. Second, they do not rely on human perceptual data of HDR image quality for re-calibration. Third, they facilitate the alignment and prioritization of specific luminance ranges for more accurate and detailed quality assessment. Experimental results show that our HDR quality metrics consistently outperform existing models in terms of quality assessment on four HDR image quality datasets and perceptual optimization of HDR novel view synthesis.

Robert Kerschner, Rakesh John Amala Arokia Nathan, Rafal Mantiuk et al.

Both humans and computational methods struggle to discriminate the depths of objects hidden beneath foliage. However, such discrimination becomes feasible when we combine computational optical synthetic aperture sensing with the human ability to fuse stereoscopic images. For object identification tasks, as required in search and rescue, wildlife observation, surveillance, and early wildfire detection, depth assists in differentiating true from false findings, such as people, animals, or vehicles vs. sun-heated patches at the ground level or in the tree crowns, or ground fires vs. tree trunks. We used video captured by a drone above dense woodland to test users' ability to discriminate depth. We found that this is impossible when viewing monoscopic video and relying on motion parallax. The same was true with stereoscopic video because of the occlusions caused by foliage. However, when synthetic aperture sensing was used to reduce occlusions and disparity-scaled stereoscopic video was presented, whereas computational (stereoscopic matching) methods were unsuccessful, human observers successfully discriminated depth. This shows the potential of systems which exploit the synergy between computational methods and human vision to perform tasks that neither can perform alone.

Aliaksei Mikhailiuk, Clifford Wilmot, Maria Perez-Ortiz et al.

Pairwise comparison data arise in many domains with subjective assessment experiments, for example in image and video quality assessment. In these experiments observers are asked to express a preference between two conditions. However, many pairwise comparison protocols require a large number of comparisons to infer accurate scores, which may be unfeasible when each comparison is time-consuming (e.g. videos) or expensive (e.g. medical imaging). This motivates the use of an active sampling algorithm that chooses only the most informative pairs for comparison. In this paper we propose ASAP, an active sampling algorithm based on approximate message passing and expected information gain maximization. Unlike most existing methods, which rely on partial updates of the posterior distribution, we are able to perform full updates and therefore much improve the accuracy of the inferred scores. The algorithm relies on three techniques for reducing computational cost: inference based on approximate message passing, selective evaluations of the information gain, and selecting pairs in a batch that forms a minimum spanning tree of the inverse of information gain. We demonstrate, with real and synthetic data, that ASAP offers the highest accuracy of inferred scores compared to the existing methods. We also provide an open-source GPU implementation of ASAP for large-scale experiments.

Yancheng Cai, Ali Bozorgian, Maliha Ashraf et al.

The perception of flicker has been a prominent concern in illumination and electronic display fields for over a century. Traditional approaches often rely on Critical Flicker Frequency (CFF), primarily suited for high-contrast (full-on, full-off) flicker. To tackle varying contrast flicker, the International Committee for Display Metrology (ICDM) introduced a Temporal Contrast Sensitivity Function TCSF$_{IDMS}$ within the Information Display Measurements Standard (IDMS). Nevertheless, this standard overlooks crucial parameters: luminance, eccentricity, and area. Existing models incorporating these parameters are inadequate for flicker detection, especially at low spatial frequencies. To address these limitations, we extend the TCSF$_{IDMS}$ and combine it with a new spatial probability summation model to incorporate the effects of luminance, eccentricity, and area (elaTCSF). We train the elaTCSF on various flicker detection datasets and establish the first variable refresh rate flicker detection dataset for further verification. Additionally, we contribute to resolving a longstanding debate on whether the flicker is more visible in peripheral vision. We demonstrate how elaTCSF can be used to predict flicker due to low-persistence in VR headsets, identify flicker-free VRR operational ranges, and determine flicker sensitivity in lighting design.

Yancheng Cai, Fei Yin, Dounia Hammou et al.

Computer vision foundation models, such as DINO or OpenCLIP, are trained in a self-supervised manner on large image datasets. Analogously, substantial evidence suggests that the human visual system (HVS) is influenced by the statistical distribution of colors and patterns in the natural world, characteristics also present in the training data of foundation models. The question we address in this paper is whether foundation models trained on natural images mimic some of the low-level characteristics of the human visual system, such as contrast detection, contrast masking, and contrast constancy. Specifically, we designed a protocol comprising nine test types to evaluate the image encoders of 45 foundation and generative models. Our results indicate that some foundation models (e.g., DINO, DINOv2, and OpenCLIP), share some of the characteristics of human vision, but other models show little resemblance. Foundation models tend to show smaller sensitivity to low contrast and rather irregular responses to contrast across frequencies. The foundation models show the best agreement with human data in terms of contrast masking. Our findings suggest that human vision and computer vision may take both similar and different paths when learning to interpret images of the real world. Overall, while differences remain, foundation models trained on vision tasks start to align with low-level human vision, with DINOv2 showing the closest resemblance.

Chenliang Zhou, Alejandro Sztrajman, Gilles Rainer et al.

We introduce the physically based neural bidirectional reflectance distribution function (PBNBRDF), a novel, continuous representation for material appearance based on neural fields. Our model accurately reconstructs real-world materials while uniquely enforcing physical properties for realistic BRDFs, specifically Helmholtz reciprocity via reparametrization and energy passivity via efficient analytical integration. We conduct a systematic analysis demonstrating the benefits of adhering to these physical laws on the visual quality of reconstructed materials. Additionally, we enhance the color accuracy of neural BRDFs by introducing chromaticity enforcement supervising the norms of RGB channels. Through both qualitative and quantitative experiments on multiple databases of measured real-world BRDFs, we show that adhering to these physical constraints enables neural fields to more faithfully and stably represent the original data and achieve higher rendering quality.

Dounia Hammou, Yancheng Cai, Pavan Madhusudanarao et al.

Image and video quality metrics, such as SSIM, LPIPS, and VMAF, are aimed to predict the perceived quality of the evaluated content and are often claimed to be "perceptual". Yet, few metrics directly model human visual perception, and most rely on hand-crafted formulas or training datasets to achieve alignment with perceptual data. In this paper, we propose a set of tests for full-reference quality metrics that examine their ability to model several aspects of low-level human vision: contrast sensitivity, contrast masking, and contrast matching. The tests are meant to provide additional scrutiny for newly proposed metrics. We use our tests to analyze 33 existing image and video quality metrics and find their strengths and weaknesses, such as the ability of LPIPS and MS-SSIM to predict contrast masking and poor performance of VMAF in this task. We further find that the popular SSIM metric overemphasizes differences in high spatial frequencies, but its multi-scale counterpart, MS-SSIM, addresses this shortcoming. Such findings cannot be easily made using existing evaluation protocols.

Yancheng Cai, Robert Wanat, Rafal Mantiuk

Accurate measurement of images produced by electronic displays is critical for the evaluation of both traditional and computational displays. Traditional display measurement methods based on sparse radiometric sampling and fitting a model are inadequate for capturing spatially varying display artifacts, as they fail to capture high-frequency and pixel-level distortions. While cameras offer sufficient spatial resolution, they introduce optical, sampling, and photometric distortions. Furthermore, the physical measurement must be combined with a model of a visual system to assess whether the distortions are going to be visible. To enable perceptual assessment of displays, we propose a combination of a camera-based reconstruction pipeline with a visual difference predictor, which account for both the inaccuracy of camera measurements and visual difference prediction. The reconstruction pipeline combines HDR image stacking, MTF inversion, vignetting correction, geometric undistortion, homography transformation, and color correction, enabling cameras to function as precise display measurement instruments. By incorporating a Visual Difference Predictor (VDP), our system models the visibility of various stimuli under different viewing conditions for the human visual system. We validate the proposed CameraVDP framework through three applications: defective pixel detection, color fringing awareness, and display non-uniformity evaluation. Our uncertainty analysis framework enables the estimation of the theoretical upper bound for defect pixel detection performance and provides confidence intervals for VDP quality scores.

Behnaz Kavoosighafi, Rafal K. Mantiuk, Saghi Hajisharif et al.

Accurately evaluating the quality of bidirectional reflectance distribution function (BRDF) models is essential for photo-realistic rendering. Traditional BRDF-space metrics often employ numerical error measures that fail to capture perceptual differences evident in rendered images. In this paper, we introduce the first perceptually informed neural quality metric for BRDF evaluation that operates directly in BRDF space, eliminating the need for rendering during quality assessment. Our metric is implemented as a compact multi-layer perceptron (MLP), trained on a dataset of measured BRDFs supplemented with synthetically generated data and labelled using a perceptually validated image-space metric. The network takes as input paired samples of reference and approximated BRDFs and predicts their perceptual quality in terms of just-objectionable-difference (JOD) scores. We show that our neural metric achieves significantly higher correlation with human judgments than existing BRDF-space metrics. While its performance as a loss function for BRDF fitting remains limited, the proposed metric offers a perceptually grounded alternative for evaluating BRDF models.

Yixu Chen, Bowen Chen, Hai Wei et al.

This paper reports IEEE International Conference on Multimedia \& Expo (ICME) 2025 Grand Challenge on Generalizable HDR and SDR Video Quality Measurement. With the rapid development of video technology, especially High Dynamic Range (HDR) and Standard Dynamic Range (SDR) contents, the need for robust and generalizable Video Quality Assessment (VQA) methods has become increasingly demanded. Existing VQA models often struggle to deliver consistent performance across varying dynamic ranges, distortion types, and diverse content. This challenge was established to benchmark and promote VQA approaches capable of jointly handling HDR and SDR content. In the final evaluation phase, five teams submitted seven models along with technical reports to the Full Reference (FR) and No Reference (NR) tracks. Among them, four methods outperformed VMAF baseline, while the top-performing model achieved state-of-the-art performance, setting a new benchmark for generalizable video quality assessment.

Rafal K. Mantiuk, Param Hanji, Maliha Ashraf et al.

ColorVideoVDP is a video and image quality metric that models spatial and temporal aspects of vision, for both luminance and color. The metric is built on novel psychophysical models of chromatic spatiotemporal contrast sensitivity and cross-channel contrast masking. It accounts for the viewing conditions, geometric, and photometric characteristics of the display. It was trained to predict common video streaming distortions (e.g. video compression, rescaling, and transmission errors), and also 8 new distortion types related to AR/VR displays (e.g. light source and waveguide non-uniformities). To address the latter application, we collected our novel XR-Display-Artifact-Video quality dataset (XR-DAVID), comprised of 336 distorted videos. Extensive testing on XR-DAVID, as well as several datasets from the literature, indicate a significant gain in prediction performance compared to existing metrics. ColorVideoVDP opens the doors to many novel applications which require the joint automated spatiotemporal assessment of luminance and color distortions, including video streaming, display specification and design, visual comparison of results, and perceptually-guided quality optimization.

Gabriel Eilertsen, Saghi Hajisharif, Param Hanji et al.

Single-image high dynamic range (SI-HDR) reconstruction has recently emerged as a problem well-suited for deep learning methods. Each successive technique demonstrates an improvement over existing methods by reporting higher image quality scores. This paper, however, highlights that such improvements in objective metrics do not necessarily translate to visually superior images. The first problem is the use of disparate evaluation conditions in terms of data and metric parameters, calling for a standardized protocol to make it possible to compare between papers. The second problem, which forms the main focus of this paper, is the inherent difficulty in evaluating SI-HDR reconstructions since certain aspects of the reconstruction problem dominate objective differences, thereby introducing a bias. Here, we reproduce a typical evaluation using existing as well as simulated SI-HDR methods to demonstrate how different aspects of the problem affect objective quality metrics. Surprisingly, we found that methods that do not even reconstruct HDR information can compete with state-of-the-art deep learning methods. We show how such results are not representative of the perceived quality and that SI-HDR reconstruction needs better evaluation protocols.

Aamir Mustafa, Aliaksei Mikhailiuk, Dan Andrei Iliescu et al.

The choice of a loss function is an important factor when training neural networks for image restoration problems, such as single image super resolution. The loss function should encourage natural and perceptually pleasing results. A popular choice for a loss is a pre-trained network, such as VGG, which is used as a feature extractor for computing the difference between restored and reference images. However, such an approach has multiple drawbacks: it is computationally expensive, requires regularization and hyper-parameter tuning, and involves a large network trained on an unrelated task. Furthermore, it has been observed that there is no single loss function that works best across all applications and across different datasets. In this work, we instead propose to train a set of loss functions that are application specific in nature. Our loss function comprises a series of discriminators that are trained to detect and penalize the presence of application-specific artifacts. We show that a single natural image and corresponding distortions are sufficient to train our feature extractor that outperforms state-of-the-art loss functions in applications like single image super resolution, denoising, and JPEG artifact removal. Finally, we conclude that an effective loss function does not have to be a good predictor of perceived image quality, but instead needs to be specialized in identifying the distortions for a given restoration method.

Param Hanji, Fangcheng Zhong, Rafal K. Mantiuk

A near-optimal reconstruction of the radiance of a High Dynamic Range scene from an exposure stack can be obtained by modeling the camera noise distribution. The latent radiance is then estimated using Maximum Likelihood Estimation. But this requires a well-calibrated noise model of the camera, which is difficult to obtain in practice. We show that an unbiased estimation of comparable variance can be obtained with a simpler Poisson noise estimator, which does not require the knowledge of camera-specific noise parameters. We demonstrate this empirically for four different cameras, ranging from a smartphone camera to a full-frame mirrorless camera. Our experimental results are consistent for simulated as well as real images, and across different camera settings.

Aamir Mustafa, Rafal K. Mantiuk

Scarcity of labeled data has motivated the development of semi-supervised learning methods, which learn from large portions of unlabeled data alongside a few labeled samples. Consistency Regularization between model's predictions under different input perturbations, particularly has shown to provide state-of-the art results in a semi-supervised framework. However, most of these method have been limited to classification and segmentation applications. We propose Transformation Consistency Regularization, which delves into a more challenging setting of image-to-image translation, which remains unexplored by semi-supervised algorithms. The method introduces a diverse set of geometric transformations and enforces the model's predictions for unlabeled data to be invariant to those transformations. We evaluate the efficacy of our algorithm on three different applications: image colorization, denoising and super-resolution. Our method is significantly data efficient, requiring only around 10 - 20% of labeled samples to achieve similar image reconstructions to its fully-supervised counterpart. Furthermore, we show the effectiveness of our method in video processing applications, where knowledge from a few frames can be leveraged to enhance the quality of the rest of the movie.

Maria Perez-Ortiz, Peter Tino, Rafal Mantiuk et al.

Data augmentation is rapidly gaining attention in machine learning. Synthetic data can be generated by simple transformations or through the data distribution. In the latter case, the main challenge is to estimate the label associated to new synthetic patterns. This paper studies the effect of generating synthetic data by convex combination of patterns and the use of these as unsupervised information in a semi-supervised learning framework with support vector machines, avoiding thus the need to label synthetic examples. We perform experiments on a total of 53 binary classification datasets. Our results show that this type of data over-sampling supports the well-known cluster assumption in semi-supervised learning, showing outstanding results for small high-dimensional datasets and imbalanced learning problems.

Jing Li, Rafal K. Mantiuk, Junle Wang et al.

In this paper we present a hybrid active sampling strategy for pairwise preference aggregation, which aims at recovering the underlying rating of the test candidates from sparse and noisy pairwise labelling. Our method employs Bayesian optimization framework and Bradley-Terry model to construct the utility function, then to obtain the Expected Information Gain (EIG) of each pair. For computational efficiency, Gaussian-Hermite quadrature is used for estimation of EIG. In this work, a hybrid active sampling strategy is proposed, either using Global Maximum (GM) EIG sampling or Minimum Spanning Tree (MST) sampling in each trial, which is determined by the test budget. The proposed method has been validated on both simulated and real-world datasets, where it shows higher preference aggregation ability than the state-of-the-art methods.

Maria Perez-Ortiz, Rafal K. Mantiuk

Most popular strategies to capture subjective judgments from humans involve the construction of a unidimensional relative measurement scale, representing order preferences or judgments about a set of objects or conditions. This information is generally captured by means of direct scoring, either in the form of a Likert or cardinal scale, or by comparative judgments in pairs or sets. In this sense, the use of pairwise comparisons is becoming increasingly popular because of the simplicity of this experimental procedure. However, this strategy requires non-trivial data analysis to aggregate the comparison ranks into a quality scale and analyse the results, in order to take full advantage of the collected data. This paper explains the process of translating pairwise comparison data into a measurement scale, discusses the benefits and limitations of such scaling methods and introduces a publicly available software in Matlab. We improve on existing scaling methods by introducing outlier analysis, providing methods for computing confidence intervals and statistical testing and introducing a prior, which reduces estimation error when the number of observers is low. Most of our examples focus on image quality assessment.

Gabriel Eilertsen, Joel Kronander, Gyorgy Denes et al.

Camera sensors can only capture a limited range of luminance simultaneously, and in order to create high dynamic range (HDR) images a set of different exposures are typically combined. In this paper we address the problem of predicting information that have been lost in saturated image areas, in order to enable HDR reconstruction from a single exposure. We show that this problem is well-suited for deep learning algorithms, and propose a deep convolutional neural network (CNN) that is specifically designed taking into account the challenges in predicting HDR values. To train the CNN we gather a large dataset of HDR images, which we augment by simulating sensor saturation for a range of cameras. To further boost robustness, we pre-train the CNN on a simulated HDR dataset created from a subset of the MIT Places database. We demonstrate that our approach can reconstruct high-resolution visually convincing HDR results in a wide range of situations, and that it generalizes well to reconstruction of images captured with arbitrary and low-end cameras that use unknown camera response functions and post-processing. Furthermore, we compare to existing methods for HDR expansion, and show high quality results also for image based lighting. Finally, we evaluate the results in a subjective experiment performed on an HDR display. This shows that the reconstructed HDR images are visually convincing, with large improvements as compared to existing methods.

Vamsi Kiran Adhikarla, Marek Vinkler, Denis Sumin et al.

Light fields become a popular representation of three dimensional scenes, and there is interest in their processing, resampling, and compression. As those operations often result in loss of quality, there is a need to quantify it. In this work, we collect a new dataset of dense reference and distorted light fields as well as the corresponding quality scores which are scaled in perceptual units. The scores were acquired in a subjective experiment using an interactive light-field viewing setup. The dataset contains typical artifacts that occur in light-field processing chain due to light-field reconstruction, multi-view compression, and limitations of automultiscopic displays. We test a number of existing objective quality metrics to determine how well they can predict the quality of light fields. We find that the existing image quality metrics provide good measures of light-field quality, but require dense reference light- fields for optimal performance. For more complex tasks of comparing two distorted light fields, their performance drops significantly, which reveals the need for new, light-field-specific metrics.

Nanyang Ye, Zhanxing Zhu, Rafal K. Mantiuk

Minimizing non-convex and high-dimensional objective functions is challenging, especially when training modern deep neural networks. In this paper, a novel approach is proposed which divides the training process into two consecutive phases to obtain better generalization performance: Bayesian sampling and stochastic optimization. The first phase is to explore the energy landscape and to capture the "fat" modes; and the second one is to fine-tune the parameter learned from the first phase. In the Bayesian learning phase, we apply continuous tempering and stochastic approximation into the Langevin dynamics to create an efficient and effective sampler, in which the temperature is adjusted automatically according to the designed "temperature dynamics". These strategies can overcome the challenge of early trapping into bad local minima and have achieved remarkable improvements in various types of neural networks as shown in our theoretical analysis and empirical experiments.