# Reposing Humans by Warping 3D Features

arXiv: https://arxiv.org/abs/2006.04898 · HTML: https://mlsanity.com/paper/2006.04898/

## Key facts

- Cited by 13 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 8 Jun 2020.

## Built on by (most cited first, 13 of 13)

- [Generative Neural Articulated Radiance Fields](https://mlsanity.com/paper/2206.14314/) (2022)
- [Control-NeRF: Editable Feature Volumes for Scene Rendering and Manipulation](https://mlsanity.com/paper/2204.10850/) (2022)
- [InsetGAN for Full-Body Image Generation](https://mlsanity.com/paper/2203.07293/) (2022)
- [Learning Realistic Human Reposing using Cyclic Self-Supervision with 3D Shape, Pose, and Appearance Consistency](https://mlsanity.com/paper/2110.05458/) (2021)
- [Flow Guided Transformable Bottleneck Networks for Motion Retargeting](https://mlsanity.com/paper/2106.07771/) (2021)
- [SCULPT: Shape-Conditioned Unpaired Learning of Pose-dependent Clothed and Textured Human Meshes](https://mlsanity.com/paper/2308.10638/) (2023)
- [GaussiGAN: Controllable Image Synthesis with 3D Gaussians from Unposed Silhouettes](https://mlsanity.com/paper/2106.13215/) (2021)
- [FDA-GAN: Flow-based Dual Attention GAN for Human Pose Transfer](https://mlsanity.com/paper/2112.00281/) (2021)
- [Diffusion-HPC: Synthetic Data Generation for Human Mesh Recovery in Challenging Domains](https://mlsanity.com/paper/2303.09541/) (2023)
- [Total Selfie: Generating Full-Body Selfies](https://mlsanity.com/paper/2308.14740/) (2023)
- [Diversity-Aware Sign Language Production through a Pose Encoding Variational Autoencoder](https://mlsanity.com/paper/2405.10423/) (2024)
- [Are Pose Estimators Ready for the Open World? STAGE: A GenAI Toolkit for Auditing 3D Human Pose Estimators](https://mlsanity.com/paper/2408.16536/) (2024)
- [HOReeNet: 3D-aware Hand-Object Grasping Reenactment](https://mlsanity.com/paper/2211.06195/) (2022)

## Abstract (arXiv)

We address the problem of reposing an image of a human into any desired novel pose. This conditional image-generation task requires reasoning about the 3D structure of the human, including self-occluded body parts. Most prior works are either based on 2D representations or require fitting and manipulating an explicit 3D body mesh. Based on the recent success in deep learning-based volumetric representations, we propose to implicitly learn a dense feature volume from human images, which lends itself to simple and intuitive manipulation through explicit geometric warping. Once the latent feature volume is warped according to the desired pose change, the volume is mapped back to RGB space by a convolutional decoder. Our state-of-the-art results on the DeepFashion and the iPER benchmarks indicate that dense volumetric human representations are worth investigating in more detail.