Image de couverture de livre

One Model, Two Minds: Task-Conditioned Reasoning for Unified Image Quality and Aesthetic Assessment

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Yin, Wen, Liu, Cencen, Liu, Dingrui, Su, Bing, Li, Yuan-Fang, He, Tao
Format:	Preprint
Publié:	2026
Sujets:	Computer Vision and Pattern Recognition
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

TiCAL:Typicality-Based Consistency-Aware Learning for Multimodal Emotion Recognition
par: Yin, Wen, et autres
Publié: (2025)

UNIAA: A Unified Multi-modal Image Aesthetic Assessment Baseline and Benchmark
par: Zhou, Zhaokun, et autres
Publié: (2024)

UniQA: Unified Vision-Language Pre-training for Image Quality and Aesthetic Assessment
par: Zhou, Hantao, et autres
Publié: (2024)

SA-IQA: Redefining Image Quality Assessment for Spatial Aesthetics with Multi-Dimensional Rewards
par: Gao, Yuan, et autres
Publié: (2025)

From Concepts to Judgments: Interpretable Image Aesthetic Assessment
par: Liu, Xiao-Chang, et autres
Publié: (2026)

A Task is Worth One Word: Learning with Task Prompts for High-Quality Versatile Image Inpainting
par: Zhuang, Junhao, et autres
Publié: (2023)

Burst Image Quality Assessment: A New Benchmark and Unified Framework for Multiple Downstream Tasks
par: Liang, Xiaoye, et autres
Publié: (2025)

MedQ-UNI: Toward Unified Medical Image Quality Assessment and Restoration via Vision-Language Modeling
par: Liu, Jiyao, et autres
Publié: (2026)

Scaling Up Personalized Image Aesthetic Assessment via Task Vector Customization
par: Yun, Jooyeol, et autres
Publié: (2024)

Can We Build Scene Graphs, Not Classify Them? FlowSG: Progressive Image-Conditioned Scene Graph Generation with Flow Matching
par: Hu, Xin, et autres
Publié: (2026)

UniPercept: Towards Unified Perceptual-Level Image Understanding across Aesthetics, Quality, Structure, and Texture
par: Cao, Shuo, et autres
Publié: (2025)

VersusQ: Pairwise Margin Reasoning for Generalizable Video Quality Assessment
par: Meng, Shibei, et autres
Publié: (2026)

Building Reasonable Inference for Vision-Language Models in Blind Image Quality Assessment
par: Li, Yuan, et autres
Publié: (2025)

Multi-Granularity Reasoning for Image Quality Assessment via Attribute-Aware Reinforcement Learning to Rank
par: Chen, Xiangyong, et autres
Publié: (2026)

IQA-Spider: Unifying Multi-Granularity Image Quality Assessment with Reasoning, Grounding and Referring
par: Peng, Xinge, et autres
Publié: (2026)

Bridging Cognitive Gap: Hierarchical Description Learning for Artistic Image Aesthetics Assessment
par: Liu, Henglin, et autres
Publié: (2025)

Image Aesthetics Assessment via Learnable Queries
par: Xiong, Zhiwei, et autres
Publié: (2023)

VisJudge-Bench: Aesthetics and Quality Assessment of Visualizations
par: Xie, Yupeng, et autres
Publié: (2025)

AlignVAR: Towards Globally Consistent Visual Autoregression for Image Super-Resolution
par: Liu, Cencen, et autres
Publié: (2026)

Understanding Pure Textual Reasoning for Blind Image Quality Assessment
par: Li, Yuan, et autres
Publié: (2026)

Learning to Look before Learning to Like: Incorporating Human Visual Cognition into Aesthetic Quality Assessment
par: Yu, Liwen, et autres
Publié: (2026)

An Order-Complexity Aesthetic Assessment Model for Aesthetic-aware Music Recommendation
par: Jin, Xin, et autres
Publié: (2024)

VENTURA: Adapting Image Diffusion Models for Unified Task Conditioned Navigation
par: Zhang, Arthur, et autres
Publié: (2025)

Image Quality Assessment for Embodied AI
par: Li, Chunyi, et autres
Publié: (2025)

Q-Ponder: A Unified Training Pipeline for Reasoning-based Visual Quality Assessment
par: Cai, Zhuoxuan, et autres
Publié: (2025)

Enhancing Image Aesthetics with Dual-Conditioned Diffusion Models Guided by Multimodal Perception
par: Nan, Xinyu, et autres
Publié: (2026)

Multi-modal Learnable Queries for Image Aesthetics Assessment
par: Xiong, Zhiwei, et autres
Publié: (2024)

SDXS: Real-Time One-Step Latent Diffusion Models with Image Conditions
par: Song, Yuda, et autres
Publié: (2024)

OneReward: Unified Mask-Guided Image Generation via Multi-Task Human Preference Learning
par: Gong, Yuan, et autres
Publié: (2025)

PosterCraft: Rethinking High-Quality Aesthetic Poster Generation in a Unified Framework
par: Chen, SiXiang, et autres
Publié: (2025)

UARE: A Unified Vision-Language Model for Image Quality Assessment, Restoration, and Enhancement
par: Li, Weiqi, et autres
Publié: (2025)

MMGen: Unified Multi-modal Image Generation and Understanding in One Go
par: Wang, Jiepeng, et autres
Publié: (2025)

Aesthetic Image Captioning with Saliency Enhanced MLLMs
par: Tao, Yilin, et autres
Publié: (2025)

MDIQA: Unified Image Quality Assessment for Multi-dimensional Evaluation and Restoration
par: Yao, Shunyu, et autres
Publié: (2025)

Grounding-IQA: Grounding Multimodal Language Model for Image Quality Assessment
par: Chen, Zheng, et autres
Publié: (2024)

DRIP: Discriminative Rotation-Invariant Pole Landmark Descriptor for 3D LiDAR Localization
par: Li, Dingrui, et autres
Publié: (2024)

2AFC Prompting of Large Multimodal Models for Image Quality Assessment
par: Zhu, Hanwei, et autres
Publié: (2024)

Enhancing Zero-shot Personalized Image Aesthetics Assessment with Profile-aware Multimodal LLM
par: Wang, Chun, et autres
Publié: (2026)

A$^3$: Towards Advertising Aesthetic Assessment
par: Ji, Kaiyuan, et autres
Publié: (2026)

Viewport-Unaware Blind Omnidirectional Image Quality Assessment: A Unified and Generalized Approach
par: Yan, Jiebin, et autres
Publié: (2026)