E2052 - MultiRef-Compass: Towards Comprehensive Evaluation of Multi-Reference-to-Audio-Video Generation
Published: July 18, 2026
Duration: 20:51
🤗 Upvotes: 29 | cs.CV, cs.SD
Authors:
Xiaohan Zhang, Yuqing Wen, Junlin Chen, Yuqi Tang, Yiting He, Lizhuo Shao, Weiming Zhu, Tengfei Liu, Yang Shi, Jialu Chen, Yuanxing Zhang, Huaxiong Li
Title:
MultiRef-Compass: Towards Comprehensive Evaluation of Multi-Reference-to-Audio-Video Generation
Arxiv:
http://arxiv.org/abs/2607.14189v1
Abstract:
Multi-reference-to-audio-video (MR2AV) generation aims to generate coherent audio-video content conditioned on multiple references and textual instructions. Existing benchmarks mainly focus on text-driven generation, single-reference subject preservation, or isolated audio-video alignment, leaving the emerging MR2AV setting largely unexplored. Compared with these set...