Skip to yearly menu bar Skip to main content


Poster

ViewFusion: Towards Multi-View Consistency via Interpolated Denoising

Xianghui Yang · Gil Avraham · Yan Zuo · Sameera Ramasinghe · Loris Bazzani · Anton van den Hengel

Arch 4A-E Poster #22
[ ] [ Paper PDF ]
[ Poster
Thu 20 Jun 10:30 a.m. PDT — noon PDT

Abstract:

Novel-view synthesis through diffusion models has demonstrated remarkable potential for generating diverse and high-quality images. Yet, the independent process of image generation in these prevailing methods leads to challenges in maintaining multiple view consistency. To address this, we introduce ViewFusion, a novel, training-free algorithm that can be seamlessly integrated into existing pre-trained diffusion models. Our approach adopts an auto-regressive method that implicitly leverages previously generated views as context for next view generation, ensuring robust multi-view consistency during the novel-view generation process. Through a diffusion process that fuses known-view information via interpolated denoising, our framework successfully extends single-view conditioned models to work in multiple-view conditional settings without any additional fine-tuning. Extensive experimental results demonstrate the effectiveness of ViewFusion in generating consistent and detailed novel views.

Chat is not available.