Abstract We introduce Zero-1-to-3, a framework for changing the camera viewpoint of an
object given just a single RGB image. To perform novel view synthesis in this …

Recent advancements in 3D reconstruction from single images have been driven by the
evolution of generative models. Prominent among these are methods based on Score …

A central goal of visual recognition is to understand objects and scenes from a single image.
2D recognition has witnessed tremendous progress thanks to large-scale learning and …

While surface-based view synthesis algorithms are appealing due to their low computational
requirements, they often struggle to reproduce thin structures. In contrast, more expensive …

We propose a 3D generation pipeline that uses diffusion models to generate realistic human
digital avatars. Due to the wide variety of human identities, poses, and stochastic details, the …

Our goal is to efficiently learn personalized animatable 3D head avatars from videos that are
geometrically accurate, realistic, relightable, and compatible with current rendering systems …

Neural implicit methods have achieved high-quality 3D object surfaces under slight specular
highlights. However, high specular reflections (HSR) often appear in front of target objects …

Abstract We introduce Tree-D Fusion, featuring the first collection of 600,000
environmentally aware, 3D simulation-ready tree models generated through Diffusion priors …

We propose a novel method for 3D object reconstruction from a sparse set of views captured
from a 360-degree calibrated camera rig. We represent the object surface through a hybrid …

Despite exciting progress in automatic 3D reconstruction from images excessive and
irregular triangular faces in the resulting meshes still constitute a significant challenge when …