Human pose estimation aims to locate the human body parts and build human body
representation (eg, body skeleton) from input data such as images and videos. It has drawn …

Abstract Three-dimensional (3D) human pose estimation involves estimating the articulated
3D joint locations of a human body from an image or video. Due to its widespread …

Deep generative models are becoming increasingly powerful, now generating diverse high
fidelity photo-realistic samples given text prompts. Have they reached the point where …

3D avatar creation plays a crucial role in the digital age. However, the whole production
process is prohibitively time-consuming and labor-intensive. To democratize this technology …

We investigate the potential of learning visual representations using synthetic images
generated by text-to-image models. This is a natural question in the light of the excellent …

Recent image generation models such as Stable Diffusion have exhibited an impressive
ability to generate fairly realistic images starting from a simple text prompt. Could such …

We show, for the first time, that neural networks trained only on synthetic data achieve state-
of-the-art accuracy on the problem of 3D human pose and shape (HPS) estimation from real …

Unsupervised learning of 3D-aware generative adversarial networks (GANs) using only
collections of single-view 2D photographs has very recently made much progress. These 3D …

We demonstrate that it is possible to perform face-related computer vision in the wild using
synthetic data alone. The community has long enjoyed the benefits of synthesizing training …

We introduce HuMoR: a 3D Human Motion Model for Robust Estimation of temporal pose
and shape. Though substantial progress has been made in estimating 3D human motion …