In most Computer Vision applications, Deep Learning models achieve state-of-the-art
performances. One drawback of Deep Learning is the large amount of data needed to train …

Generating synthetic datasets for training face recognition models is challenging because
dataset generation entails more than creating high fidelity images. It involves generating …

We present a foundation model for zero-shot metric monocular depth estimation. Our model,
Depth Pro, synthesizes high-resolution depth maps with unparalleled sharpness and high …

Recovering a skeletal shape from a monocular video is a longstanding challenge. Prevailing
nonrigid animal reconstruction methods often adopt a control-point driven animation model …

We are living in a three-dimensional space while moving forward through a fourth
dimension: time. To allow artificial intelligence to develop a comprehensive understanding …

Despite the growing demand for accurate surface normal estimation models existing
methods use general-purpose dense prediction models adopting the same inductive biases …

Image-and video-based 3D human recovery (ie, pose and shape estimation) have achieved
substantial progress. However, due to the prohibitive cost of motion capture, existing …

Point cloud scene flow estimation is of practical importance for dynamic scene navigation in
autonomous driving. Since scene flow labels are hard to obtain, current methods train their …

Building 3D geometric maps of man-made spaces is a well-established and active field that
is fundamental to numerous computer vision and robotics applications. However …

Abstract Amodal Instance Segmentation (AIS) endeavors to accurately deduce complete
object shapes that are partially or fully occluded. However, the inherent ill-posed nature of …