LongAV-Compass: Towards Unified Evaluation of Minute-Scale Audio-Visual Generation Across T2AV, I2AV, and V2AV
Quick Take
LongAV-Compass introduces a benchmark for minute-scale audio-visual generation across T2AV, I2AV, and V2AV, featuring 284 test cases and over 20 evaluation dimensions. This framework enhances understanding of identity consistency and narrative coherence in extended content, addressing gaps in existing short-form evaluation protocols.
Key Points
- LongAV-Compass features 284 curated test cases for diverse audio-visual generation scenarios.
- Benchmark evaluates T2AV, I2AV, and V2AV generation complexities systematically.
- Framework integrates MLLM-assisted assessment with perceptual and multimodal metrics.
- Over 20 evaluation dimensions cover quality, consistency, coherence, and synchronization.
- Experiments validate limitations of current models in maintaining coherent minute-scale generation.
Article Content
From source RSS / original summaryarXiv:2605. 26244v1 Announce Type: new Abstract: Audio-visual generation is rapidly advancing from short clips to minute-long content, while existing evaluation protocols remain largely confined to short-form settings. Existing benchmarks primarily focus on 5--10 second text-conditioned generation and rarely support unified evaluation across text, image, and video conditioning modalities.
Moreover, they provide limited insight into how identity consistency, narrative coherence, and audio-visual alignment degrade over extended temporal horizons. To bridge this gap, we introduce LongAV-Compass, a systematic benchmark for minute-long audio-visual generation. LongAV-Compass contains 284 curated test cases spanning text-to-audio-video (T2AV), image-to-audio-video (I2AV), and video-to-audio-video (V2AV), organized by application scenario and generation complexity.
The benchmark combines taxonomy-guided benchmark construction with a unified evaluation framework that integrates MLLM-assisted assessment with complementary perceptual and multimodal metrics, including DINO-v2, ArcFace, CLIP, and ImageBind. The framework evaluates more than 20 fine-grained dimensions covering within-segment quality, cross-segment consistency, global narrative coherence, semantic alignment, and audio-visual synchronization.
Through experiments on 11 representative models together with human-alignment validation, LongAV-Compass provides a diagnostic testbed for analyzing the limitations of current systems in sustaining coherent, semantically aligned, and temporally consistent minute-scale audio-visual generation across diverse input modalities.
Reader Mode unavailable (could not extract clean content).
Want this in your inbox every morning?
Daily brief at your local 8am — bilingual EN/中文, free.
More from arXiv cs.CV
See more →Evi-Steer: Learning to Steer Biomedical Vision-Language Models through Efficient and Generalizable Evidential Tuning
Evi-Steer introduces a novel evidential tuning framework for BiomedCLIP, achieving 0.11% parameter updates while enhancing uncertainty-aware fine-tuning. It outperforms state-of-the-art methods across 15 biomedical imaging datasets, proving effective in few-shot learning and domain shifts for clinical applications.