Lifting 2D diffusion for 3D generation is a challenging problem due to the lack of geometric
prior and the complex entanglement of materials and lighting in natural images. Existing …

We release MiDaS v3. 1 for monocular depth estimation, offering a variety of new models
based on different encoder backbones. This release is motivated by the success of …

Manually creating 3D environments for AR/VR applications is a complex process requiring
expert knowledge in 3D modeling software. Pioneering works facilitate this process by …

We are witnessing significant breakthroughs in the technology for generating 3D objects
from text. Existing approaches either leverage large text-to-image models to optimize a 3D …

We introduce a novel 3D generative method Generative 3D Reconstruction (G3DR) in
ImageNet capable of generating diverse and high-quality 3D objects from single images …

The problem of novel view synthesis has grown significantly in popularity recently with the
introduction of Neural Radiance Fields (NeRFs) and other implicit scene representation …

Significant advances have been made in human-centric video generation, yet the joint video-
depth generation problem remains underexplored. Most existing monocular depth …

There is a bias in the inference pipeline of most diffusion models. This bias arises from a
signal leak whose distribution deviates from the noise distribution, creating a discrepancy …

Dynamic novel view synthesis aims to capture the temporal evolution of visual content within
videos. Existing methods struggle to distinguishing between motion and structure …

In this paper, we present a method for generating consistent novel views from a single
source image. Our approach focuses on maximizing the reuse of visible pixels from the …