Pith. sign in

REVIEW 9 cited by

Adaptive Image Quality Assessment via Teaching Large Multimodal Model to Compare

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2405.19298 v1 pith:CKPFJ2R3 submitted 2024-05-29 cs.CV eess.IV

Hanwei Zhu , Haoning Wu , Yixuan Li , Zicheng Zhang , Baoliang Chen , Lingyu Zhu , Yuming Fang , Guangtao Zhai
show 2 more authors
Weisi Lin Shiqi Wang
This is my paper · ORCID
classification cs.CVeess.IV
keywords qualitycomparativeimageduringinferencescoretrainingassessment
verification ladder T0 review T1 audit T2 compute T3 formal

Signed reviews

No signed human review yet.

0 comments
read the original abstract

While recent advancements in large multimodal models (LMMs) have significantly improved their abilities in image quality assessment (IQA) relying on absolute quality rating, how to transfer reliable relative quality comparison outputs to continuous perceptual quality scores remains largely unexplored. To address this gap, we introduce Compare2Score-an all-around LMM-based no-reference IQA (NR-IQA) model, which is capable of producing qualitatively comparative responses and effectively translating these discrete comparative levels into a continuous quality score. Specifically, during training, we present to generate scaled-up comparative instructions by comparing images from the same IQA dataset, allowing for more flexible integration of diverse IQA datasets. Utilizing the established large-scale training corpus, we develop a human-like visual quality comparator. During inference, moving beyond binary choices, we propose a soft comparison method that calculates the likelihood of the test image being preferred over multiple predefined anchor images. The quality score is further optimized by maximum a posteriori estimation with the resulting probability matrix. Extensive experiments on nine IQA datasets validate that the Compare2Score effectively bridges text-defined comparative levels during training with converted single image quality score for inference, surpassing state-of-the-art IQA models across diverse scenarios. Moreover, we verify that the probability-matrix-based inference conversion not only improves the rating accuracy of Compare2Score but also zero-shot general-purpose LMMs, suggesting its intrinsic effectiveness.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 9 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. Multimodal LLMs Can Reason about Aesthetics in Zero-Shot

    cs.CV 2025-01 conditional novelty 7.0 of 10

    A zero-shot two-stage prompting baseline (ArtCoT) makes multimodal LLMs' aesthetic judgments align substantially better with human expert rankings in pairwise artwork comparisons.

  2. From Global to Granular: Revealing IQA Model Performance via Correlation Surface

    cs.CV 2026-01 conditional novelty 6.0 of 10

    GMC maps an IQA model's agreement with human scores across the quality-level and quality-difference landscape, exposing local strengths that global PLCC/SRCC hide.

  3. Creative4U: MLLMs-based Advertising Creative Image Selector with Comparative Reasoning

    cs.CV 2025-08 conditional novelty 6.0 of 10

    A multimodal language model, trained on a new annotated image-pair dataset and a recall-precision reinforcement reward, selects better advertising creatives and explains its choices, with measured offline and online gains.

  4. Q-Ponder: A Unified Training Pipeline for Reasoning-based Visual Quality Assessment

    cs.CV 2025-06 conditional novelty 6.0 of 10

    Q-Ponder is a two-stage pipeline (distill-then-reinforce) that makes a 7B multimodal model both more accurate at image quality scoring and better at explaining its judgments.

  5. LLM-based Evaluation Policy Extraction for Ecological Modeling

    cs.AI 2025-05 conditional novelty 6.0 of 10

    APEF learns interpretable evaluation policies for ecological time-series models by combining an LLM-driven weight optimizer with human or predefined pairwise preference annotations.

  6. Generalizable Video Quality Assessment via Weak-to-Strong Learning

    cs.CV 2025-05 unverdicted novelty 6.0 of 10

    Self-supervised ranking-based training on a 10x larger unlabeled video dataset enables a VQA model to match supervised zero-shot performance, show strong OOD generalization, and set new SOTA when fine-tuned.

  7. Towards Unified Benchmark and Models for Multi-Modal Perceptual Metrics

    cs.CV 2024-12 conditional novelty 6.0 of 10

    A new benchmark and fine-tuned models show that multi-task training improves average perceptual-similarity accuracy on known tasks but does not generalize to out-of-distribution perceptual tasks.

  8. AdaQual-Diff: Diffusion-Based Image Restoration via Adaptive Quality Prompting

    cs.CV 2025-04 conditional novelty 5.0 of 10

    Using DeQAScore-derived quality maps to scale diffusion prompt complexity per region improves restoration PSNR, by roughly 1.4 dB over OneRestore on CDD-11 and less than 0.1 dB over T3-DiffWeather on most weather benchmarks.

  9. DeQA-Doc: Adapting DeQA-Score to Document Image Quality Assessment

    cs.CV 2025-07 conditional novelty 4.0 of 10

    DeQA-Doc adapts DeQA-Score, an MLLM-based image quality scorer, to document images using pseudo-variance soft labels and resolution-flexible encoders, and reports top scores on DIQA-5000.

Pith tools