# Pose-Guided Human Animation from a Single Image in the Wild

arXiv: https://arxiv.org/abs/2012.03796 · HTML: https://mlsanity.com/paper/2012.03796/

## Key facts

- Cited by 53 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 7 Dec 2020.

## Built on by (most cited first, 30 of 53)

- [Animatable Neural Radiance Fields for Modeling Dynamic Human Bodies](https://mlsanity.com/paper/2105.02872/) (2021)
- [Champ: Controllable and Consistent Human Image Animation with 3D Parametric Guidance](https://mlsanity.com/paper/2403.14781/) (2024)
- [MixSTE: Seq2seq Mixed Spatio-Temporal Encoder for 3D Human Pose Estimation in Video](https://mlsanity.com/paper/2203.00859/) (2022)
- [DisCo: Disentangled Control for Realistic Human Dance Generation](https://mlsanity.com/paper/2307.00040/) (2023)
- [Real-time Deep Dynamic Characters](https://mlsanity.com/paper/2105.01794/) (2021)
- [EVA3D: Compositional 3D Human Generation from 2D Image Collections](https://mlsanity.com/paper/2210.04888/) (2022)
- [Neural Actor: Neural Free-view Synthesis of Human Actors with Pose Control](https://mlsanity.com/paper/2106.02019/) (2021)
- [AvatarCLIP: Zero-Shot Text-Driven Generation and Animation of 3D Avatars](https://mlsanity.com/paper/2205.08535/) (2022)
- [Style and Pose Control for Image Synthesis of Humans from a Single Monocular View](https://mlsanity.com/paper/2102.11263/) (2021)
- [Putting People in Their Place: Affordance-Aware Human Insertion into Scenes](https://mlsanity.com/paper/2304.14406/) (2023)
- [Watch It Move: Unsupervised Discovery of 3D Joints for Re-Posing of Articulated Objects](https://mlsanity.com/paper/2112.11347/) (2021)
- [HumanGAN: A Generative Model of Humans Images](https://mlsanity.com/paper/2103.06902/) (2021)
- [Pose with Style: Detail-Preserving Pose-Guided Image Synthesis with Conditional StyleGAN](https://mlsanity.com/paper/2109.06166/) (2021)
- [Single-Image 3D Human Digitization with Shape-Guided Diffusion](https://mlsanity.com/paper/2311.09221/) (2023)
- [One-shot Implicit Animatable Avatars with Model-based Priors](https://mlsanity.com/paper/2212.02469/) (2022)
- [Structure-Aware Motion Transfer with Deformable Anchor Model](https://mlsanity.com/paper/2204.05018/) (2022)
- [Animatable Implicit Neural Representations for Creating Realistic Avatars from Videos](https://mlsanity.com/paper/2203.08133/) (2022)
- [Text2Human: Text-Driven Controllable Human Image Generation](https://mlsanity.com/paper/2205.15996/) (2022)
- [A Comprehensive Survey on Human Video Generation: Challenges, Methods, and Insights](https://mlsanity.com/paper/2407.08428/) (2024)
- [Dressing in the Wild by Watching Dance Videos](https://mlsanity.com/paper/2203.15320/) (2022)
- [AvatarFusion: Zero-shot Generation of Clothing-Decoupled 3D Avatars Using 2D Diffusion](https://mlsanity.com/paper/2307.06526/) (2023)
- [HUMBI: A Large Multiview Dataset of Human Body Expressions and Benchmark Challenge](https://mlsanity.com/paper/2110.00119/) (2021)
- [Deep Person Generation: A Survey from the Perspective of Face, Pose and Cloth Synthesis](https://mlsanity.com/paper/2109.02081/) (2021)
- [Jointly Harnessing Prior Structures and Temporal Consistency for Sign Language Video Generation](https://mlsanity.com/paper/2207.03714/) (2022)
- [DanceTogether! Identity-Preserving Multi-Person Interactive Video Generation](https://mlsanity.com/paper/2505.18078/) (2025)
- [Learning Motion-Dependent Appearance for High-Fidelity Rendering of Dynamic Humans from a Single Camera](https://mlsanity.com/paper/2203.12780/) (2022)
- [Human Image Generation: A Comprehensive Survey](https://mlsanity.com/paper/2212.08896/) (2022)
- [CAMM: Building Category-Agnostic and Animatable 3D Models from Monocular Videos](https://mlsanity.com/paper/2304.06937/) (2023)
- [Conditional Temporal Variational AutoEncoder for Action Video Prediction](https://mlsanity.com/paper/2108.05658/) (2021)
- [Collaborative Neural Rendering using Anime Character Sheets](https://mlsanity.com/paper/2207.05378/) (2022)

## Abstract (arXiv)

We present a new pose transfer method for synthesizing a human animation from a single image of a person controlled by a sequence of body poses. Existing pose transfer methods exhibit significant visual artifacts when applying to a novel scene, resulting in temporal inconsistency and failures in preserving the identity and textures of the person. To address these limitations, we design a compositional neural network that predicts the silhouette, garment labels, and textures. Each modular network is explicitly dedicated to a subtask that can be learned from the synthetic data. At the inference time, we utilize the trained network to produce a unified representation of appearance and its labels in UV coordinates, which remains constant across poses. The unified representation provides an incomplete yet strong guidance to generating the appearance in response to the pose change. We use the trained network to complete the appearance and render it with the background. With these strategies, we are able to synthesize human animations that can preserve the identity and appearance of the person in a temporally coherent way without any fine-tuning of the network on the testing scene. Experiments show that our method outperforms the state-of-the-arts in terms of synthesis quality, temporal coherence, and generalization ability.