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.
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.