Skip to yearly menu bar Skip to main content


SPAD: Spatially Aware Multi-View Diffusers

Yash Kant · Aliaksandr Siarohin · Ziyi Wu · Michael Vasilkovsky · Guocheng Qian · Jian Ren · Riza Alp Guler · Bernard Ghanem · Sergey Tulyakov · Igor Gilitschenski

Arch 4A-E Poster #36
[ ] [ Project Page ]
Thu 20 Jun 10:30 a.m. PDT — noon PDT


We present SPAD, a novel approach for creating consistent multi-view images from text prompts or single images. To enable multi-view generation, we repurpose a pretrained 2D diffusion model by extending its self-attention layers with cross-view interactions, and fine-tune it on a high quality subset of Objaverse. We find that a naive extension of the self-attention proposed in prior work (e.g., MVDream) leads to content copying between views. Therefore, we explicitly constrain the cross-view attention based on epipolar geometry. To further enhance 3D consistency, we utilize Pl ╠łucker coordinates derived from camera rays and inject them as positional encoding. This enables SPAD to reason over spatial proximity in 3D well. Compared to concurrent works that can only generate views at fixed azimuth and elevation (e.g., MVDream, SyncDreamer), SPAD offers full camera control and achieves state-of-the-art results in novel view synthesis on unseen objects from the Objaverse and Google Scanned Objects datasets. Finally, we demonstrate that text-to-3D generation using SPAD prevents the multi-face Janus issue.

Live content is unavailable. Log in and register to view live content