ReLIQS is a CLIP-based multiscale patch-driven architecture that is resolution-agnostic, preserves original-resolution quality cues, learns from multiple subjective studies, and remains computationally efficient and budget-adaptive.
Abstract
No-reference image quality assessment (NR IQA) has recently benefited from deep and multimodal models, yet many SOTA systems still violate at least one basic requirement: they either discard critical quality cues via aggressive resizing, fail to generalize across resolutions, cannot be jointly trained on heterogeneous IQA datasets with mismatched MOS scales, or require prohibitive computation. We present \textbf{ReLIQS}, a model for \textbf{Re}solution-agnostic \textbf{L}earning for \textbf{I}mage \textbf{Q}uality with \textbf{S}aliency, which is resolution-agnostic, preserves original-resolution quality cues, learns from multiple subjective studies, and remains computationally efficient and budget-adaptive. ReLIQS is a CLIP-based multiscale patch-driven architecture that learns both \emph{where to look} and \emph{how to judge} quality. Fixed-size patches are sampled across multiple resolutions, including the original resolution, and encoded with a CLIP vision backbone. A lightweight Perceptual Importance Estimator then predicts IQA-specific importance maps to select a small set of informative patches, and a Latent Quality Axis Module aggregates their embeddings into a single image-level score. Across authentic, synthetic, and AIGC benchmarks spanning diverse resolutions and distortions, ReLIQS generalizes better than strong CNN-, CLIP-, and MLLM-based baselines with matching or reduced computational cost.
This model leverages different layers of the large language model (LLM) decoder, treating them as multiple detectors that perform synchronous distortion detection using multi-level features, which helps mitigate the ambiguous foreground-background separation commonly encountered in the S2A problem.
Ziheng Jia, Yingji Liang, Jiaying Qian et al.· 0 citations
Blind Image Quality Assessment (BIQA) models trained on one distortion distribution often degrade when exposed to new ones, making sequential adaptation without forgetting a fundamental challenge. While continual learning offers a natural solution, existing methods typically retrain the entire backbone per task, limiting scalability and parameter efficiency. We propose ContEditIQA, a parameter-efficient framework for continual BIQA that selectively edits a pre-trained Vision Transformer (ViT) rather than retraining it. Following a locate-then-edit strategy, a lightweight attention-guided hypernetwork identifies distortion-sensitive Feed-Forward Network (FFN) parameters for each incoming task and restricts updates to those regions, while attention layers remain frozen to preserve globally shared representations. This targeted editing enables robust sequential adaptation without model expansion or memory replay. Experiments across six BIQA benchmarks demonstrate superior knowledge retention and cross-dataset generalization while modifying fewer than 30% of backbone parameters, establishing selective model editing as an effective and scalable paradigm for continual BIQA.
Satish Maurya, Parimala Kancharla· International Conference on...· 0 citations
G2D is proposed, a training-free framework that uses a generative VLM to verify CLIP-retrieved candidates against the image and transfers to DCLIP, WaffleCLIP, and CuPL, supporting a practical interface between discriminative proposal and generative visual reasoning.
Zehua Hao, Fang Liu, Qinliang Wang et al.· 0 citations
This paper presents doctoral research on adaptive video super-resolution and perceptual quality modeling under real-world conditions. Existing video super-resolution (VSR) methods struggle to generalize under unknown degradations arising from heterogeneous devices, codecs, and network environments. We address this challenge through test-time adaptation (TTA), a unified paradigm that improves robustness and perceptual quality without retraining or high-quality supervision. Specifically, we: 1) propose a TTA-based framework for no-reference video quality assessment (VQA), where adapted quality predictions provide perceptual guidance for VSR under unseen distortions; 2) develop a transformer-based architecture for screen-content super-resolution that preserves text clarity and structural fidelity; and 3) introduce a region-aware TTA strategy that selectively refines text and non-text regions without requiring high-resolution ground truth. Experimental results across diverse benchmarks demonstrate consistent improvements in perceptual quality and readability. We also outline ongoing work toward fully adaptive video enhancement systems capable of generalizing across unseen domains.
AI-generated image quality assessment (AIGIQA) requires jointly reasoning about perceptual fidelity and prompt alignment, two quality dimensions that are often treated as independent in existing AIGIQA models. However, by reexamining human ratings, we uncover a previously overlooked phenomenon: the two dimensions are interdependent and exhibit both competitive and cooperative interactions during human rating. This observation suggests that a unified model should neither collapse the two dimensions nor rigidly separate them, but rather adaptively negotiate their interplay. Motivated by this insight, we introduce an interaction-aware learning framework that models perception-alignment relations through adversarial and collaborative inference pathways. Instead of designing a rigid dual-branch architecture, our method employs a gated interaction module that dynamically routes features according to the inferred relationship between the two dimensions. Task-aware prompts further modulate the gating behaviour, enabling the model to switch between competition and cooperation when necessary. Experiments across multiple AIGIQA benchmarks demonstrate that our approach not only achieves state-of-the-art accuracy but also yields interpretable interaction patterns, offering a more faithful approximation of human judgment. The codes are available at https://github.com/LQAMEI/ACL-IQA.
High similarity between first-visit and return frames does not necessarily show that a video world model remembered the scene; the intervening rollout may simply have changed very little. This ambiguity makes absolute revisit scores sensitive to rendering stability, repetitive content, and failed motion. We introduce \emph{R2M-Bench} (\textbf{R}elative \textbf{R}evisit \textbf{M}emory Benchmark), a benchmark of observable revisit-selective consistency. For every detected return, R2M-Bench compares the revisit pair with two controls from the same rollout: a gap-matched non-revisit pair that measures generic temporal stability and a short-range pair that estimates short-horizon consistency. These comparisons produce \emph{MemoryGain} (MG), the revisit advantage over the temporal baseline, and the \emph{Normalized Memory Ratio} (NMR), which normalizes this advantage by the short-to-baseline dynamic range. R2M-Bench combines 100 reference scenes with three leave-and-return trajectories to form 300 instances and evaluates appearance fidelity, scene and object identity, local geometry, and persistent state. Across seven action-conditioned video world models, Overall NMR correlates with human consistency judgments at Spearman's $\rho=0.547$ (95\% CI $[0.45,0.63]$). Its within-model correlation magnitude with generated motion is $0.072$, compared with $0.207$ for raw revisit similarity, indicating that relative calibration substantially reduces the slow-motion shortcut. DreamX-World-Memo achieves the highest Overall NMR among the evaluated video models. Together, these results support same-rollout relative calibration as a practical way to distinguish revisit-specific consistency from generic temporal stability.
Qiwen Gu, Bingjie Gao, Rui Chen et al.· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
