VFusion3D: Learning Scalable 3D Generative Models from Video Diffusion Models

arXiv:2403.12034v1 Announce Type: cross
Abstract: This paper presents a novel paradigm for building scalable 3D generative models utilizing pre-trained video diffusion models. The primary obstacle in developing foundation 3D generative models is the limited availability of 3D data. Unlike images, texts, or videos, 3D data are not readily accessible and are difficult to acquire. This results in a significant disparity in scale compared to the vast quantities of other types of data. To address this issue, we propose using a …

abstract arxiv availability building cs.cv cs.gr cs.lg data diffusion diffusion models foundation generative generative models images novel paper paradigm scalable type video video diffusion videos