1

We extend deferred neural rendering to articulated settings, specifically humans, and demonstrate fast and high quality rendering performance.

A very efficient differentiable renderer, tightly integrated with PyTorch and PyTorch3D.

We propose a new method to reconstruct a mesh-based avatar from RGB-D video taking albedo and lighting into account.

We propose a novel, end-to-end pipeline to reconstruct detailed animatable avatars from a single picture.

Extending cycle consistency models to learn mappings between 2D images and parameterized 3D models.

We propose a novel representation, Basis Point Sets (BPS), for point clouds that allows us to perform deep learning tasks naturally and efficiently.

We propose a novel end-to-end neural network architecture and training scheme to train 3D body pose and shape estimation from 2D images.

Existing markerless motion capture methods often assume known backgrounds, static cameras, and sequence specific motion priors, limiting their application scenarios. Here we present a fully automatic method that, given multiview videos, estimates 3D …

We propose an end-to-end trainable neural network that can generate images of people in clothing. It can be conditioned on pose, body shape and clothing color.

We propose an annotation pipeline and models for detailed 3D human body model fits to 2D images. In this paper, we explore models with up to 91 keypoints and 32 semantic body part segments.