Saved in:
| Main Authors: | , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2509.24427 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866916976182427648 |
|---|---|
| author | Zhang, Ailing Lei, Lina Kong, Dehong Wang, Zhixin Xu, Jiaqi Song, Fenglong Guo, Chun-Le Liu, Chang Li, Fan Chen, Jie |
| author_facet | Zhang, Ailing Lei, Lina Kong, Dehong Wang, Zhixin Xu, Jiaqi Song, Fenglong Guo, Chun-Le Liu, Chang Li, Fan Chen, Jie |
| contents | Generative diffusion models are developing rapidly and attracting increasing attention due to their wide range of applications. Image-to-Video (I2V) generation has become a major focus in the field of video synthesis. However, existing evaluation benchmarks primarily focus on aspects such as video quality and temporal consistency, while largely overlooking the model's ability to understand the semantics of specific subjects in the input image or to ensure that the generated video aligns with physical laws and human commonsense. To address this gap, we propose UI2V-Bench, a novel benchmark for evaluating I2V models with a focus on semantic understanding and reasoning. It introduces four primary evaluation dimensions: spatial understanding, attribute binding, category understanding, and reasoning. To assess these dimensions, we design two evaluation methods based on Multimodal Large Language Models (MLLMs): an instance-level pipeline for fine-grained semantic understanding, and a feedback-based reasoning pipeline that enables step-by-step causal assessment for more accurate evaluation. UI2V-Bench includes approximately 500 carefully constructed text-image pairs and evaluates a range of both open source and closed-source I2V models across all defined dimensions. We further incorporate human evaluations, which show strong alignment with the proposed MLLM-based metrics. Overall, UI2V-Bench fills a critical gap in I2V evaluation by emphasizing semantic comprehension and reasoning ability, offering a robust framework and dataset to support future research and model development in the field. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_24427 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | UI2V-Bench: An Understanding-based Image-to-video Generation Benchmark Zhang, Ailing Lei, Lina Kong, Dehong Wang, Zhixin Xu, Jiaqi Song, Fenglong Guo, Chun-Le Liu, Chang Li, Fan Chen, Jie Computer Vision and Pattern Recognition Generative diffusion models are developing rapidly and attracting increasing attention due to their wide range of applications. Image-to-Video (I2V) generation has become a major focus in the field of video synthesis. However, existing evaluation benchmarks primarily focus on aspects such as video quality and temporal consistency, while largely overlooking the model's ability to understand the semantics of specific subjects in the input image or to ensure that the generated video aligns with physical laws and human commonsense. To address this gap, we propose UI2V-Bench, a novel benchmark for evaluating I2V models with a focus on semantic understanding and reasoning. It introduces four primary evaluation dimensions: spatial understanding, attribute binding, category understanding, and reasoning. To assess these dimensions, we design two evaluation methods based on Multimodal Large Language Models (MLLMs): an instance-level pipeline for fine-grained semantic understanding, and a feedback-based reasoning pipeline that enables step-by-step causal assessment for more accurate evaluation. UI2V-Bench includes approximately 500 carefully constructed text-image pairs and evaluates a range of both open source and closed-source I2V models across all defined dimensions. We further incorporate human evaluations, which show strong alignment with the proposed MLLM-based metrics. Overall, UI2V-Bench fills a critical gap in I2V evaluation by emphasizing semantic comprehension and reasoning ability, offering a robust framework and dataset to support future research and model development in the field. |
| title | UI2V-Bench: An Understanding-based Image-to-video Generation Benchmark |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2509.24427 |