Hadi Amirpour

Wei Zhou, Yixiao Li, Hadi Amirpour et al.

Single-image super-resolution (SR) has achieved remarkable progress with deep learning, yet most approaches rely on distortion-oriented losses or heuristic perceptual priors, which often lead to a trade-off between fidelity and visual quality. To address this issue, we propose an \textit{Efficient Perceptual Bi-directional Attention Network (Efficient-PBAN)} that explicitly optimizes SR towards human-preferred quality. Unlike patch-based quality models, Efficient-PBAN avoids extensive patch sampling and enables efficient image-level perception. The proposed framework is trained on our self-constructed SR quality dataset that covers a wide range of state-of-the-art SR methods with corresponding human opinion scores. Using this dataset, Efficient-PBAN learns to predict perceptual quality in a way that correlates strongly with subjective judgments. The learned metric is further integrated into SR training as a differentiable perceptual loss, enabling closed-loop alignment between reconstruction and perceptual assessment. Extensive experiments demonstrate that our approach delivers superior perceptual quality. Code is publicly available at https://github.com/Lighting-YXLI/Efficient-PBAN.

Yixiao Li, Xin Li, Chris Wei Zhou et al.

This paper presents the ISRGC-Q Challenge, built upon the Image Super-Resolution Generated Content Quality Assessment (ISRGen-QA) dataset, and organized as part of the Visual Quality Assessment (VQualA) Competition at the ICCV 2025 Workshops. Unlike existing Super-Resolution Image Quality Assessment (SR-IQA) datasets, ISRGen-QA places a greater emphasis on SR images generated by the latest generative approaches, including Generative Adversarial Networks (GANs) and diffusion models. The primary goal of this challenge is to analyze the unique artifacts introduced by modern super-resolution techniques and to evaluate their perceptual quality effectively. A total of 108 participants registered for the challenge, with 4 teams submitting valid solutions and fact sheets for the final testing phase. These submissions demonstrated state-of-the-art (SOTA) performance on the ISRGen-QA dataset. The project is publicly available at: https://github.com/Lighting-YXLI/ISRGen-QA.

Yirui Zeng, Jun Fu, Hadi Amirpour et al.

Blind dehazed image quality assessment (BDQA), which aims to accurately predict the visual quality of dehazed images without any reference information, is essential for the evaluation, comparison, and optimization of image dehazing algorithms. Existing learning-based BDQA methods have achieved remarkable success, while the small scale of DQA datasets limits their performance. To address this issue, in this paper, we propose to adapt Contrastive Language-Image Pre-Training (CLIP), pre-trained on large-scale image-text pairs, to the BDQA task. Specifically, inspired by the fact that the human visual system understands images based on hierarchical features, we take global and local information of the dehazed image as the input of CLIP. To accurately map the input hierarchical information of dehazed images into the quality score, we tune both the vision branch and language branch of CLIP with prompt learning. Experimental results on two authentic DQA datasets demonstrate that our proposed approach, named CLIP-DQA, achieves more accurate quality predictions over existing BDQA methods. The code is available at https://github.com/JunFu1995/CLIP-DQA.

Yuqing Luo, Yixiao Li, Jiang Liu et al.

Image complexity assessment (ICA) is a challenging task in perceptual evaluation due to the subjective nature of human perception and the inherent semantic diversity in real-world images. Existing ICA methods predominantly rely on hand-crafted or shallow convolutional neural network-based features of a single visual modality, which are insufficient to fully capture the perceived representations closely related to image complexity. Recently, cross-modal scene semantic information has been shown to play a crucial role in various computer vision tasks, particularly those involving perceptual understanding. However, the exploration of cross-modal scene semantic information in the context of ICA remains unaddressed. Therefore, in this paper, we propose a novel ICA method called Cross-Modal Scene Semantic Alignment (CM-SSA), which leverages scene semantic alignment from a cross-modal perspective to enhance ICA performance, enabling complexity predictions to be more consistent with subjective human perception. Specifically, the proposed CM-SSA consists of a complexity regression branch and a scene semantic alignment branch. The complexity regression branch estimates image complexity levels under the guidance of the scene semantic alignment branch, while the scene semantic alignment branch is used to align images with corresponding text prompts that convey rich scene semantic information by pair-wise learning. Extensive experiments on several ICA datasets demonstrate that the proposed CM-SSA significantly outperforms state-of-the-art approaches. Codes are available at https://github.com/XQ2K/First-Cross-Model-ICA.

Wei Zhou, Hadi Amirpour, Christian Timmerer et al.

As multimedia services such as video streaming, video conferencing, virtual reality (VR), and online gaming continue to expand, ensuring high perceptual visual quality becomes a priority to maintain user satisfaction and competitiveness. However, multimedia content undergoes various distortions during acquisition, compression, transmission, and storage, resulting in the degradation of experienced quality. Thus, perceptual visual quality assessment (PVQA), which focuses on evaluating the quality of multimedia content based on human perception, is essential for optimizing user experiences in advanced communication systems. Several challenges are involved in the PVQA process, including diverse characteristics of multimedia content such as image, video, VR, point cloud, mesh, multimodality, etc., and complex distortion scenarios as well as viewing conditions. In this paper, we first present an overview of PVQA principles and methods. This includes both subjective methods, where users directly rate their experiences, and objective methods, where algorithms predict human perception based on measurable factors such as bitrate, frame rate, and compression levels. Based on the basics of PVQA, quality predictors for different multimedia data are then introduced. In addition to traditional images and videos, immersive multimedia and generative artificial intelligence (GenAI) content are also discussed. Finally, the paper concludes with a discussion on the future directions of PVQA research.

Sizhuo Ma, Wei-Ting Chen, Qiang Gao et al.

Face images play a crucial role in numerous applications; however, real-world conditions frequently introduce degradations such as noise, blur, and compression artifacts, affecting overall image quality and hindering subsequent tasks. To address this challenge, we organized the VQualA 2025 Challenge on Face Image Quality Assessment (FIQA) as part of the ICCV 2025 Workshops. Participants created lightweight and efficient models (limited to 0.5 GFLOPs and 5 million parameters) for the prediction of Mean Opinion Scores (MOS) on face images with arbitrary resolutions and realistic degradations. Submissions underwent comprehensive evaluations through correlation metrics on a dataset of in-the-wild face images. This challenge attracted 127 participants, with 1519 final submissions. This report summarizes the methodologies and findings for advancing the development of practical FIQA approaches.

Zhihao Guo, Jingxuan Su, Shenglin Wang et al.

3D Gaussian Splatting has emerged as an efficient photorealistic novel view synthesis method. However, its reliance on sparse Structure-from-Motion (SfM) point clouds often limits scene reconstruction quality. To address the limitation, this paper proposes a novel 3D reconstruction framework, Gaussian Processes enhanced Gaussian Splatting (GP-GS), in which a multi-output Gaussian Process model is developed to enable adaptive and uncertainty-guided densification of sparse SfM point clouds. Specifically, we propose a dynamic sampling and filtering pipeline that adaptively expands the SfM point clouds by leveraging GP-based predictions to infer new candidate points from the input 2D pixels and depth maps. The pipeline utilizes uncertainty estimates to guide the pruning of high-variance predictions, ensuring geometric consistency and enabling the generation of dense point clouds. These densified point clouds provide high-quality initial 3D Gaussians, enhancing reconstruction performance. Extensive experiments conducted on synthetic and real-world datasets across various scales validate the effectiveness and practicality of the proposed framework.

MohammadAli Hamidi, Hadi Amirpour, Luigi Atzori et al.

Face image quality assessment (FIQA) plays a critical role in face recognition and verification systems, especially in uncontrolled, real-world environments. Although several methods have been proposed, general-purpose no-reference image quality assessment techniques often fail to capture face-specific degradations. Meanwhile, state-of-the-art FIQA models tend to be computationally intensive, limiting their practical applicability. We propose a lightweight and efficient method for FIQA, designed for the perceptual evaluation of face images in the wild. Our approach integrates an ensemble of two compact convolutional neural networks, MobileNetV3-Small and ShuffleNetV2, with prediction-level fusion via simple averaging. To enhance alignment with human perceptual judgments, we employ a correlation-aware loss (MSECorrLoss), combining mean squared error (MSE) with a Pearson correlation regularizer. Our method achieves a strong balance between accuracy and computational cost, making it suitable for real-world deployment. Experiments on the VQualA FIQA benchmark demonstrate that our model achieves a Spearman rank correlation coefficient (SRCC) of 0.9829 and a Pearson linear correlation coefficient (PLCC) of 0.9894, remaining within competition efficiency constraints.

Xuecheng Wu, Dingkang Yang, Danlei Huang et al.

Short-form videos (SVs) have become a vital part of our online routine for acquiring and sharing information. Their multimodal complexity poses new challenges for video analysis, highlighting the need for video emotion analysis (VEA) within the community. Given the limited availability of SVs emotion data, we introduce eMotions, a large-scale dataset consisting of 27,996 videos with full-scale annotations. To ensure quality and reduce subjective bias, we emphasize better personnel allocation and propose a multi-stage annotation procedure. Additionally, we provide the category-balanced and test-oriented variants through targeted sampling to meet diverse needs. While there have been significant studies on videos with clear emotional cues (e.g., facial expressions), analyzing emotions in SVs remains a challenging task. The challenge arises from the broader content diversity, which introduces more distinct semantic gaps and complicates the representations learning of emotion-related features. Furthermore, the prevalence of audio-visual co-expressions in SVs leads to the local biases and collective information gaps caused by the inconsistencies in emotional expressions. To tackle this, we propose AV-CANet, an end-to-end audio-visual fusion network that leverages video transformer to capture semantically relevant representations. We further introduce the Local-Global Fusion Module designed to progressively capture the correlations of audio-visual features. Besides, EP-CE Loss is constructed to globally steer optimizations with tripolar penalties. Extensive experiments across three eMotions-related datasets and four public VEA datasets demonstrate the effectiveness of our proposed AV-CANet, while providing broad insights for future research. Moreover, we conduct ablation studies to examine the critical components of our method. Dataset and code will be made available at Github.

Yiying Wei, Hadi Amirpour, Jong Hwan Ko et al.

Leveraging the overfitting property of deep neural networks (DNNs) is trending in video delivery systems to enhance quality within bandwidth limits. Existing approaches transmit overfitted super-resolution (SR) model streams for low-resolution (LR) bitstreams, which are used to reconstruct high-resolution (HR) videos at the decoder. Although these approaches show promising results, the huge computational costs of training a large number of video frames limit their practical applications. To overcome this challenge, we propose an efficient patch sampling method named EPS for video SR network overfitting, which identifies the most valuable training patches from video frames. To this end, we first present two low-complexity Discrete Cosine Transform (DCT)-based spatial-temporal features to measure the complexity score of each patch directly. By analyzing the histogram distribution of these features, we then categorize all possible patches into different clusters and select training patches from the cluster with the highest spatial-temporal information. The number of sampled patches is adaptive based on the video content, addressing the trade-off between training complexity and efficiency. Our method reduces the number of patches for the training to 4% to 25%, depending on the resolution and number of clusters, while maintaining high video quality and significantly enhancing training efficiency. Compared to the state-of-the-art patch sampling method, EMT, our approach achieves an 83% decrease in overall run time.

Hannaneh Barahouei Pasandi, Tamer Nadeem, Hadi Amirpour

Over the last decade, the bandwidth expansion and MU-MIMO spectral efficiency have promised to increase data throughput by allowing concurrent communication between one Access Point and multiple users. However, we are still a long way from enjoying such MU-MIMO MAC protocol improvements for bandwidth hungry applications such as video streaming in practical WiFi network settings due to heterogeneous channel conditions and devices, unreliable transmissions, and lack of useful feedback exchange among the lower and upper layers' requirements. This paper introduces MuViS, a novel dual-phase optimization framework that proposes a Quality of Experience (QoE) aware MU-MIMO optimization for multi-user video streaming over IEEE 802.11ac. MuViS first employs reinforcement learning to optimize the MU-MIMO user group and mode selection for users based on their PHY/MAC layer characteristics. The video bitrate is then optimized based on the user's mode (Multi-User (MU) or Single-User (SU)). We present our design and its evaluation on smartphones and laptops using 802.11ac WiFi. Our experimental results in various indoor environments and configurations show a scalable framework that can support a large number of users with streaming at high video rates and satisfying QoE requirements.

Ekrem Cetinkaya, Hadi Amirpour, Mohammad Ghanbari et al.

High-Efficiency Video Coding (HEVC) surpasses its predecessors in encoding efficiency by introducing new coding tools at the cost of an increased encoding time-complexity. The Coding Tree Unit (CTU) is the main building block used in HEVC. In the HEVC standard, frames are divided into CTUs with the predetermined size of up to 64x64 pixels. Each CTU is then divided recursively into a number of equally sized square areas, known as Coding Units (CUs). Although this diversity of frame partitioning increases encoding efficiency, it also causes an increase in the time complexity due to the increased number of ways to find the optimal partitioning. To address this complexity, numerous algorithms have been proposed to eliminate unnecessary searches during partitioning CTUs by exploiting the correlation in the video. In this paper, existing CTU depth decision algorithms for HEVC are surveyed. These algorithms are categorized into two groups, namely statistics and machine learning approaches. Statistics approaches are further subdivided into neighboring and inherent approaches. Neighboring approaches exploit the similarity between adjacent CTUs to limit the depth range of the current CTU, while inherent approaches use only the available information within the current CTU. Machine learning approaches try to extract and exploit similarities implicitly. Traditional methods like support vector machines or random forests use manually selected features, while recently proposed deep learning methods extract features during training. Finally, this paper discusses extending these methods to more recent video coding formats such as Versatile Video Coding (VVC) and AOMedia Video 1(AV1).

Hadi Amirpour, Antonio Pinheiro, Manuela Pereira et al.

Light field imaging is characterized by capturing brightness, color, and directional information of light rays in a scene. This leads to image representations with huge amount of data that require efficient coding schemes. In this paper, lenslet images are rendered into sub-aperture images. These images are organized as a pseudo-sequence input for the HEVC video codec. To better exploit redundancy among the neighboring sub-aperture images and consequently decrease the distances between a sub-aperture image and its references used for prediction, sub-aperture images are divided into four smaller groups that are scanned in a serpentine order. The most central sub-aperture image, which has the highest similarity to all the other images, is used as the initial reference image for each of the four regions. Furthermore, a structure is defined that selects spatially adjacent sub-aperture images as prediction references with the highest similarity to the current image. In this way, encoding efficiency increases, and furthermore it leads to a higher similarity among the co-located Coding Three Units (CTUs). The similarities among the co-located CTUs are exploited to predict Coding Unit depths.Moreover, independent encoding of each group division enables parallel processing, that along with the proposed coding unit depth prediction decrease the encoding execution time by almost 80% on average. Simulation results show that Rate-Distortion performance of the proposed method has higher compression gain than the other state-of-the-art lenslet compression methods with lower computational complexity.