ViewFusion: Towards Multi-View Consistency via Interpolated Denoising
CVPR 2024(2024)
摘要
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 the 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.
更多查看译文
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要