Salvato in:
| Autori principali: | , , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | https://arxiv.org/abs/2510.08789 |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866909841900961792 |
|---|---|
| author | Xing, Shuo Dey, Soumik Wu, Mingyang Mishra, Ashirbad Ravipati, Naveen Li, Binbin Wu, Hansi Tu, Zhengzhong |
| author_facet | Xing, Shuo Dey, Soumik Wu, Mingyang Mishra, Ashirbad Ravipati, Naveen Li, Binbin Wu, Hansi Tu, Zhengzhong |
| contents | Video quality assessment (VQA) is a fundamental computer vision task that aims to predict the perceptual quality of a given video in alignment with human judgments. Existing performant VQA models trained with direct score supervision suffer from (1) poor generalization across diverse content and tasks, ranging from user-generated content (UGC), short-form videos, to AI-generated content (AIGC), (2) limited interpretability, and (3) lack of extensibility to novel use cases or content types. We propose Q-Router, an agentic framework for universal VQA with a multi-tier model routing system. Q-Router integrates a diverse set of expert models and employs vision--language models (VLMs) as real-time routers that dynamically reason and then ensemble the most appropriate experts conditioned on the input video semantics. We build a multi-tiered routing system based on the computing budget, with the heaviest tier involving a specific spatiotemporal artifacts localization for interpretability. This agentic design enables Q-Router to combine the complementary strengths of specialized experts, achieving both flexibility and robustness in delivering consistent performance across heterogeneous video sources and tasks. Extensive experiments demonstrate that Q-Router matches or surpasses state-of-the-art VQA models on a variety of benchmarks, while substantially improving generalization and interpretability. Moreover, Q-Router excels on the quality-based question answering benchmark, Q-Bench-Video, highlighting its promise as a foundation for next-generation VQA systems. Finally, we show that Q-Router capably localizes spatiotemporal artifacts, showing potential as a reward function for post-training video generation models. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2510_08789 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Q-Router: Agentic Video Quality Assessment with Expert Model Routing and Artifact Localization Xing, Shuo Dey, Soumik Wu, Mingyang Mishra, Ashirbad Ravipati, Naveen Li, Binbin Wu, Hansi Tu, Zhengzhong Computer Vision and Pattern Recognition Video quality assessment (VQA) is a fundamental computer vision task that aims to predict the perceptual quality of a given video in alignment with human judgments. Existing performant VQA models trained with direct score supervision suffer from (1) poor generalization across diverse content and tasks, ranging from user-generated content (UGC), short-form videos, to AI-generated content (AIGC), (2) limited interpretability, and (3) lack of extensibility to novel use cases or content types. We propose Q-Router, an agentic framework for universal VQA with a multi-tier model routing system. Q-Router integrates a diverse set of expert models and employs vision--language models (VLMs) as real-time routers that dynamically reason and then ensemble the most appropriate experts conditioned on the input video semantics. We build a multi-tiered routing system based on the computing budget, with the heaviest tier involving a specific spatiotemporal artifacts localization for interpretability. This agentic design enables Q-Router to combine the complementary strengths of specialized experts, achieving both flexibility and robustness in delivering consistent performance across heterogeneous video sources and tasks. Extensive experiments demonstrate that Q-Router matches or surpasses state-of-the-art VQA models on a variety of benchmarks, while substantially improving generalization and interpretability. Moreover, Q-Router excels on the quality-based question answering benchmark, Q-Bench-Video, highlighting its promise as a foundation for next-generation VQA systems. Finally, we show that Q-Router capably localizes spatiotemporal artifacts, showing potential as a reward function for post-training video generation models. |
| title | Q-Router: Agentic Video Quality Assessment with Expert Model Routing and Artifact Localization |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2510.08789 |