arXiv subjects

Ming Ronnier Luo

Publications and source records attributed to Ming Ronnier Luo.

4 recordsLinked to original sources

arXiv2026

Evaluating Vision-Language Models for Image Quality Assessment using Psychophysical Data

Psychophysical experiments remain the most reliable approach for perceptual image quality assessment (IQA), yet their cost and limited scalability motivate automated alternatives. This paper investigates whether Vision-Language Models (VLMs) can assist in assessing perceived image appearance and quality. We introduce a psychophysics-inspired framework to probe VLM perceptual sensitivity through controlled pairwise image comparisons of contrast, colorfulness, and overall preference. Six VLMs (four proprietary and two open-weight models) are compared against psychophysical data. Results reveal strong attribute-dependent variability: Claude exhibits the highest internal consistency, whereas GPT achieves the strongest agreement for overall preference. Claude and Qwen show the strongest alignment for colorfulness, while Qwen performs best for contrast. However, no model consistently matches human perception across all attributes. High self-consistency does not necessarily imply perceptual validity, and VLM--human agreement generally improves when perceptual differences among renderings are more pronounced.

cs.CV↗

arXiv2023

Perceptual Tone Mapping Model for High Dynamic Range Imaging

One of the key challenges in tone mapping is to preserve the perceptual quality of high dynamic range (HDR) images when mapping them to standard dynamic range (SDR) displays. Traditional tone mapping operators (TMOs) compress the luminance of HDR images without considering the surround and display conditions emanating into suboptimal results. Current research addresses this challenge by incorporating perceptual color appearance attributes. In this work, we propose a TMO (TMOz) that leverages CIECAM16 perceptual attributes, i.e., brightness, colorfulness, and hue. TMOz accounts for the effects of both the surround and the display conditions to achieve more optimal colorfulness reproduction. The perceptual brightness is compressed, and the perceptual color scales, i.e., colorfulness and hue are derived from HDR images by employing CIECAM16 color adaptation equations. A psychophysical experiment was conducted to automate the brightness compression parameter. The model employs fully automatic and adaptive approach, obviating the requirement for manual parameter selection. TMOz was evaluated in terms of contrast, colorfulness and overall image quality. The objective and subjective evaluation methods revealed that the proposed model outperformed the state-of-the-art TMOs.

cs.CV↗

arXiv2019

A color-difference formula for evaluating color pairs with no separation -- $ΔE_{NS}$

All color-difference formulas are developed to evaluate color differences for pairs of stimuli with hair-line separation. In printing applications, however, color differences are frequently judged between a pair of samples with no-separation because they are printed adjacent on the same piece of paper. A new formula, dENS has been developed for pairs of stimuli with no-separation (NS). An experiment was conducted to investigate the effect of different color-difference magnitudes using sample pairs with NS. 1,012 printed pairs with NS were prepared around 11 CIE recommended color centers. The pairs, representing four color-difference magnitudes of 1, 2, 4 and 8 CIELAB units were visually evaluated by a panel of 19 observers using the gray-scale method. Comparison of the present data based on pairs with NS, and previously generated data using pairs with hair-line separation, showed a clear separation effect. A new color-difference equation for the NS viewing condition (dENS) is proposed by modifying the CIEDE2000 formula. The separation effect can be well described by the new formula. For a sample pair with NS, when the CIEDE2000 color difference is less than 9.1, a larger color difference leads to a larger lightness difference, and thus the total color difference increases. When the CIEDE2000 color difference is greater than 9.1, the effect is opposite, i.e. the lightness difference decreases, and thus the total color difference also decreases. The new formula is recommended for future research to evaluate its performance in appropriate applications.

eess.IV↗

arXiv2015

Comparing CSI and PCA in Amalgamation with JPEG for Spectral Image Compression

Continuing our previous research on color image compression, we move towards spectral image compression. This enormous amount of data needs more space to store and more time to transmit. To manage this sheer amount of data, researchers have investigated different techniques so that image quality can be conserved and compressibility can be improved. The principle component analysis (PCA) can be employed to reduce the dimensions of spectral images to achieve high compressibility and performance. Due to processing complexity of PCA, a simple interpolation technique called cubic spline interpolation (CSI) was considered to reduce the dimensionality of spectral domain of spectral images. The CSI and PCA were employed one by one in the spectral domain and were amalgamated with the JPEG, which was employed in spatial domain. Three measures including compression rate (CR), processing time (Tp) and color difference CIEDE2000 were used for performance analysis. Test results showed that for a fixed value of compression rate, CSI based algorithm performed poor in terms of dE00, in comparison with PCA, but is still reliable because of small color difference. On the other hand it has lower complexity and is computationally much better as compared to PCA based algorithm, especially for spectral images with large size.

cs.MM↗