Publication

CAMEO: Correspondence-Attention Alignment for Multi-View Diffusion Models

We propose CAMEO, a novel framework that aligns correspondence and attention maps to enable consistent multi-view generation from diffusion models.

AUTHORS Minkyung Kwon*, Jinhyeok Choi*, Jiho Park*, Seonghu Jeon, Jinhyuk Jang, Junyoung Seo, Minseop Kwak, Jin-Hwa Kim, Seungryong Kim
MY ROLE Research Contributor
VENUE arXiv preprint
DATE November 2025
LINKS Paper · Project Page
CAMEO: Correspondence-Attention Alignment for Multi-View Diffusion Models

Abstract

We present CAMEO, a method to align correspondence and attention for multi-view diffusion models. By ensuring that the attention maps across different views are consistent with the underlying geometric correspondences, we achieve significantly improved consistency in generated multi-view images.