Vision-Language Model (VLM)-based image quality assessment (IQA) has been significantly advanced by incorporating Chain-of-Thought (CoT) reasoning. Recent work has refined image quality reasoning by applying reinforcement learning (RL) and leveraging active visual tools. However, such strategies are typically language-centric, with visual information being treated as static preconditions. Quality-related visual cues often cannot be abstracted into text in extenso due to the gap between discrete textual tokens and quality perception space, which in turn restricts the reasoning effectiveness for visually intensive IQA tasks. In this paper, we revisit this by asking the question, "Is natural language the ideal space for quality reasoning?" and, as a consequence, we propose Q-Tacit, a new paradigm that elicits VLMs to reason beyond natural language in the latent quality space. Our approach follows a synergistic two-stage process: (i) injecting structural visual quality priors into the latent space, and (ii) calibrating latent reasoning trajectories to improve quality assessment ability. Extensive experiments demonstrate that Q-Tacit can effectively perform quality reasoning with significantly fewer tokens than previous reasoning-based methods, while achieving strong overall performance. This paper validates the proposition that language is not the only compact representation suitable for visual quality, opening possibilities for further exploration of effective latent reasoning paradigms for IQA. Source code will be released to support future research.
ThematicPlane: Bridging Tacit User Intent and Latent Spaces for Image Generation
Adobe Inc.（Adobe公司）；Johns Hopkins University（约翰霍普金斯大学）；University of Washington（华盛顿大学）；University of Colorado（科罗拉多大学）；University of Illinois at Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校）
In this paper, we propose a novel virtual reality image quality assessment (VR IQA) with adversarial learning for omnidirectional images. To take into account the characteristics of the omnidirectional image, we devise deep networks including novel quality score predictor and human perception guider. The proposed quality score predictor automatically predicts the quality score of distorted image using the latent spatial and position feature. The proposed human perception guider criticizes the predicted quality score of the predictor with the human perceptual score using adversarial learning. F…
Institute of Information Engineering, Chinese Academy of Sciences（中国科学院信息工程研究所）；School of Cyber Security, University of Chinese Academy of Sciences（中国科学院大学网络与信息安全学院）
Latent Graph Representations for Critical View of Safety Assessment
ICube（ICube实验室）；University of Strasbourg（斯特拉斯堡大学）；CNRS（法国国家科学研究中心）；IHU-Strasbourg（斯特拉斯堡大学医院研究所）；Institute of Image-Guided Surgery（图像引导外科研究所）；Fondazione Policlinico Universitario Agostino Gemelli IRCCS（阿戈斯蒂诺·杰梅里大学综合诊所基金会IRCCS）；Institute for Research against Digestive Cancer (IRCAD)（消化道癌症研究所（IRCAD））
Johns Hopkins University（约翰斯·霍普金斯大学）；National Institute on Aging, National Institutes of Health（美国国立卫生研究院国家衰老研究所）；Johns Hopkins School of Medicine（约翰斯·霍普金斯大学医学院）
Image quality control (IQC) can be used in automated magnetic resonance (MR) image analysis to exclude erroneous results caused by poorly acquired or artifact-laden images. Existing IQC methods for MR imaging generally require human effort to craft meaningful features or label large datasets for supervised training. The involvement of human labor can be burdensome and biased, as labeling MR images based on their quality is a subjective task. In this paper, we propose an automatic IQC method that evaluates the extent of artifacts in MR images without supervision. In particular, we design an art…
We propose a method for knowledge transfer between semantically related classes in ImageNet. By transferring knowledge from the images that have bounding-box annotations to the others, our method is capable of automatically populating ImageNet with many more bounding-boxes and even pixel-level segmentations. The underlying assumption that objects from semantically related classes look alike is formalized in our novel Associative Embedding (AE) representation. AE recovers the latent low-dimensional space of appearance variations among image windows. The dimensions of AE space tend to correspond…
Multimodal Latent Fusion of ECG Leads for Early Assessment of Pulmonary Hypertension
School of Computer Science, University of Sheffield（谢菲尔德大学计算机科学学院）；Centre for Machine Intelligence, University of Sheffield（谢菲尔德大学智能中心）；Department of Electrical & Computer Science Engineering, IITRAM Ahmedabad（印度阿赫迈德亚布德IITRAM电子与计算机科学工程系）；Digital Environment Research Institute, Queen Mary University of London（伦敦玛丽女王大学数字环境研究院）；Nepal Applied Mathematics and Informatics Institute for research (NAAMII), Nepal（尼泊尔应用数学与信息技术研究所）；Department of Computing, Imperial College London（伦敦帝国学院计算机系）；School of Medicine and Population Health, University of Sheffield（谢菲尔德大学医学与人口健康学院）；Department of Clinical Radiology, Sheffield Teaching Hospitals（谢菲尔德教学医院放射科）；National Institute for Health and Care Research (NIHR), Sheffield Biomedical Research Centre（英国国家健康与护理研究所（NIHR）谢菲尔德生物医学研究中心）
University of British Columbia（不列颠哥伦比亚大学）；Princeton University（普林斯顿大学）
High-performance deep learning methods typically rely on large annotated training datasets, which are difficult to obtain in many clinical applications due to the high cost of medical image labeling. Existing data assessment methods commonly require knowing the labels in advance, which are not feasible to achieve our goal of 'knowing which data to label.' To this end, we formulate and propose a novel and efficient data assessment strategy, EXponentiAl Marginal sINgular valuE (EXAMINE) score, to rank the quality of unlabeled medical image data based on their useful latent representations extrac…
Technion - Israel Institute of Technology（以色列理工学院）；NetApp（NetApp 公司）
The success of deep neural nets heavily relies on their ability to encode complex relations between their input and their output. While this property serves to fit the training data well, it also obscures the mechanism that drives prediction. This study aims to reveal hidden concepts by employing an intervention mechanism that shifts the predicted class based on discrete variational autoencoders. An explanatory model then visualizes the encoded information from any hidden layer and its corresponding intervened representation. By the assessment of differences between the original representation…
Cooperative Medianet Innovation Center, Shanghai Jiao Tong University（上海交通大学协同媒体创新中心）
We present a novel no-reference quality assessment metric, the image transferred point cloud quality assessment (IT-PCQA), for 3D point clouds. For quality assessment, deep neural network (DNN) has shown compelling performance on no-reference metric design. However, the most challenging issue for no-reference PCQA is that we lack large-scale subjective databases to drive robust networks. Our motivation is that the human visual system (HVS) is the decision-maker regardless of the type of media for quality assessment. Leveraging the rich subjective scores of the natural images, we can quest the …
Indian Institute of Information Technology, Design and Manufacturing Kancheepuram（印度坎奇普拉姆信息技术设计与制造学院）；Indian Institute of Technology Madras（印度理工学院马德拉斯分校）
Numerous stereoscopic 3D movies are released every year to theaters and created large revenues. Despite the improvement in stereo capturing and 3D video post-production technology, stereoscopic artifacts which cause viewer discomfort continue to appear even in high-budget films. Existing automatic 3D video quality measurement tools can detect distortions in stereoscopic images or videos, but they fail to consider the viewer's subjective perception of those artifacts, and how these distortions affect their choices. In this paper, we introduce a novel recommendation system for stereoscopic 3D mo…
