Q-Tacit: Image Quality Assessment via Latent Visual Reasoning

Yuxuan Jiang; Yixuan Li; Hanwei Zhu; Siyue Teng; Fan Zhang; David Bull

cs.CVMar 23, 2026

Q-Tacit: Image Quality Assessment via Latent Visual Reasoning

Authors: Yuxuan Jiang, Yixuan Li, Hanwei Zhu, Siyue Teng, Fan Zhang, David Bull

Organizations: Visual Information Lab, University of Bristol · Nanyang Technological University

Abstract

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.

Figures & tables

Figure 1: Motivation and overview of Q-Tacit. We compare Q-Tacit and Q-Insight [ 25 ] , which perform quality reasoning in a latent space and a text space, respectively. <|lvr_start|> and <|lvr_end|> encapsulate the latent reasoning process, and <|lvr|> is a placeholder for a latent slot token that allocates one latent reasoning step. Q-Tacit excels at image quality scoring on out-of-distribution datasets (Right) while requiring only 10% visible token counts compared to Q-Insight (Left).

Figure 2: Overview of Q-Tacit. We introduce a compact latent quality-reasoning segment wrapped by special tokens <|lvr_start|> and <|lvr_end|> , where the model propagates latent embeddings (i.e., internal hidden states) as a compact quality space instead of generating textual rationales. Then directly outputs the final quality score in <answer> and </answer> when a stopping criterion is met.

Figure 3: Example training data for Q-Tacit. The left part shows the mixture for constructing the latent space in Stage I. The Bboxes field specifies the ROI to supervise latent reconstruction. <lvr> functions as a placeholder to indicate where the latent segment should be inserted, which will expand to a series of latent span $\texttt{<|lvr\_start|>}\ \texttt{<|lvr|>}...\texttt{<|lvr|>}\texttt{<|lvr\_end|>}$ in practice. The right part is quality-aligned calibration for latent quality reasoning in Stage II.

Methods	KonIQ-10K	SPAQ	KADID	PIPAL	LIVEW	AGIQA	CSIQ	AVG.
Handcrafted
NIQE [ 35 ]	0.533	0.679	0.468	0.195	0.493	0.560	0.718	0.521
(SPL 2012)	/ 0.530	/ 0.664	/ 0.405	/ 0.161	/ 0.449	/ 0.533	/ 0.628	/ 0.481
BRISQUE [ 34 ]	0.225	0.490	0.429	0.267	0.361	0.541	0.740	0.436
(TIP 2012)	/ 0.226	/ 0.406	/ 0.356	/ 0.232	/ 0.313	/ 0.497	/ 0.556	/ 0.369
Non-VLM Deep-learning

Table 1: PLCC / SRCC results of NR-IQA models trained on KonIQ-10K . Exceptions marked with † use a multi-task training set in [ 25 ] for GRPO calibration. Top two results are highlighted in bold and underlined , respectively.

Figure 4: Token-space coupling and attention weight distribution during quality scoring: Q-Insight vs. Q-Tacit. Left/Right: t-SNE visualization of visual and reasoning tokens for Q-Insight/Q-Tacit. Middle: normalized attention weights over the image and reasoning tokens after the quality score is generated. Q-Tacit obtained similar attention allocated to reasoning with only 11 tokens (vs. 112 for Q-Insight).

Figure 5: Sensitivity to localized distortions. We compare Q-Insight, VisualQuality-R1, and Q-Tacit by reporting predicted quality scores for each image (w/o distorted patch, top) and its counterpart with a localized corruption (w/ distorted patch, bottom). Blur, noise, and compression are injected within the red box (left to right). Q-Tacit consistently lowers its predicted scores in response to the local distortion.

Panel of Table 2 — Table 2: Ablation on the effect of latent reasoning pipeline (PLCC/SRCC). We compare Q-Tacit with two variants: Stage I-only and Stage I+II w/o LVR . Top two results are highlighted in bold and underlined , respectively.

Panel of Table 3 — Table 3: Ablation on the latent space composition (PLCC/SRCC). We vary the Stage I training data on three subsets ( $\checkmark$ indicates included data), while keeping Stage II identical across rows. Top two results are highlighted in bold and underlined , respectively.

Panel of Table 4 — Table 4: Ablation on reward design (PLCC/SRCC). Q-Insight and R2RL are two different reward design, and $\tau$ is the threshold in our dense quality scoring reward. Top two results are highlighted in bold and underlined , respectively.

Panel of Table 5 — Table 5: Ablation on latent reasoning budget $T$ (PLCC/SRCC). We vary the latent-segment length $T\in\{4,16\}$ and compare with the default setting $T=8$ . Top two results are highlighted in bold and underlined , respectively.

Appendix figures & tables2 assets

Supplementary material from the paper’s appendix.

Appendix

Figure A: Qualitative score prediction examples from KADID-10k [ 27 ] . For each example, the normalized MOS as ground-truth score (GT) is shown above the image, and the bar plot compares predicted scores from Q-Tacit, Q-Insight [ 25 ] , and VisualQuality-R1 [ 58 ] . The dashed line indicates GT for easier visual comparison.

Method	#Parameters	Inference Time $\downarrow$	Inference Memory	#TFLOPs $\downarrow$
Q-Insight [ 25 ]	8.29 B	2.22 s	15.6 G	8.13
VisualQuality-R1 [ 58 ]	8.29 B	2.04 s	15.6 G	7.49
Q-Tacit(Ours)	8.29 B	0.83 s	15.6 G	6.62

Appendix

Table A: Averaged model complexity comparison using

512\times 384\times 3

images as input tested on single GH200 GPU.

Explore similar work

IQA-T1: Tool-based Visual Evidence Reasoning for Image Quality Assessment
Jul 14, 2026Jinjian Wu, Jiaqi Tang, Wei Wei +5Tool Use in VLMs VLM Reasoning
School of Computer Science, Northwestern Polytechnical University, Xi’an, China · The Hong Kong University of Science and Technology, Hong Kong SAR, China
ME-IQA: Memory-Enhanced Image Quality Assessment via Re-Ranking
Mar 21, 2026Kanglong Fan, Tianhe Wu, Wen Wen +6Memory-Augmented VLMs Vision-Language Models
City University of Hong Kong, Hong Kong SAR, China · ByteDance Inc., China
Zoom-IQA: Image Quality Assessment with Reliable Region-Aware Reasoning
Jan 6, 2026Guoqiang Liang, Jianyi Wang, Zhonghua Wu +2VLM Robustness VLM Reasoning
National University of Singapore · S-Lab, Nanyang Technological University, Singapore · SenseTime Research

Jul 14, 2026J/K move · Enter open · S save

IQA-T1: Tool-based Visual Evidence Reasoning for Image Quality Assessment

Jinjian Wu, Jiaqi Tang, Wei Wei, Yingying Yan+4

School of Computer Science, Northwestern Polytechnical University, Xi’an, China · The Hong Kong University of Science and Technology, Hong Kong SAR, China

Tool Use in VLMs VLM Reasoning Image Quality Assessment

Open paper AskPDF arXiv

Image Quality Assessment (IQA) in open-world environments remains challenging due to limited generalization and interpretability. Recent approaches based on multimodal large language models (MLLMs) introduce textual reasoning for quality prediction, yet their judgments rely heavily on semantically biased internal representations, making them insensitive to low-level perceptual degradations. We propose IQA-T1, a tool-based visual evidence reasoning framework that augments MLLM reasoning with explicit perceptual observations. During inference, the model autonomously invokes specialized analysis tools to generate structured visual evidence, such as noise residual maps, gradient statistics, and frequency spectra, which are progressively integrated into the reasoning process. To support this paradigm, we construct Q-Tool, a dataset containing 11k multimodal reasoning chains grounded in tool-generated evidence. Extensive experiments on seven IQA benchmarks show that IQA-T1 achieves the best overall performance across datasets while producing interpretable and evidence-grounded quality assessments. Code and dataset are available at https://github.com/zibuyu-02/IQA-T1.

Abstract

Explore similar work

IQA-T1: Tool-based Visual Evidence Reasoning for Image Quality Assessment

ME-IQA: Memory-Enhanced Image Quality Assessment via Re-Ranking

Zoom-IQA: Image Quality Assessment with Reliable Region-Aware Reasoning