# Free-viewpoint Human Animation with Pose-correlated Reference Selection

arXiv: https://arxiv.org/abs/2412.17290 · HTML: https://mlsanity.com/paper/2412.17290/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 35 of its 39 references that are in the map.
- First posted on arXiv 23 Dec 2024.

## Builds on (most cited first, 30 of 35)

- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [Denoising Diffusion Implicit Models](https://mlsanity.com/paper/2010.02502/) (2020)
- [DINOv2: Learning Robust Visual Features without Supervision](https://mlsanity.com/paper/2304.07193/) (2023)
- [You Only Look Once: Unified, Real-Time Object Detection](https://mlsanity.com/paper/1506.02640/) (2015)
- [First Order Motion Model for Image Animation](https://mlsanity.com/paper/2003.00196/) (2020)
- [Animate Anyone: Consistent and Controllable Image-to-Video Synthesis for Character Animation](https://mlsanity.com/paper/2311.17117/) (2023)
- [Neural Body: Implicit Neural Representations with Structured Latent Codes for Novel View Synthesis of Dynamic Humans](https://mlsanity.com/paper/2012.15838/) (2020)
- [HumanNeRF: Free-viewpoint Rendering of Moving People from Monocular Video](https://mlsanity.com/paper/2201.04127/) (2022)
- [MagicAnimate: Temporally Consistent Human Image Animation using Diffusion Model](https://mlsanity.com/paper/2311.16498/) (2023)
- [Effective Whole-body Pose Estimation with Two-stages Distillation](https://mlsanity.com/paper/2307.15880/) (2023)
- [Novel View Synthesis with Diffusion Models](https://mlsanity.com/paper/2210.04628/) (2022)
- [EDGE: Editable Dance Generation From Music](https://mlsanity.com/paper/2211.10658/) (2022)
- [Generative Novel View Synthesis with 3D-Aware Diffusion Models](https://mlsanity.com/paper/2304.02602/) (2023)
- [Champ: Controllable and Consistent Human Image Animation with 3D Parametric Guidance](https://mlsanity.com/paper/2403.14781/) (2024)
- [Thin-Plate Spline Motion Model for Image Animation](https://mlsanity.com/paper/2203.14367/) (2022)
- [MimicMotion: High-Quality Human Motion Video Generation with Confidence-aware Pose Guidance](https://mlsanity.com/paper/2406.19680/) (2024)
- [DreamGaussian4D: Generative 4D Gaussian Splatting](https://mlsanity.com/paper/2312.17142/) (2023)
- [Depth-Aware Generative Adversarial Network for Talking Head Video Generation](https://mlsanity.com/paper/2203.06605/) (2022)
- [DreamPose: Fashion Image-to-Video Synthesis via Stable Diffusion](https://mlsanity.com/paper/2304.06025/) (2023)
- [Liquid Warping GAN: A Unified Framework for Human Motion Imitation, Appearance Transfer and Novel View Synthesis](https://mlsanity.com/paper/1909.12224/) (2019)
- [DisCo: Disentangled Control for Realistic Human Dance Generation](https://mlsanity.com/paper/2307.00040/) (2023)
- [Recent Advances in 3D Gaussian Splatting](https://mlsanity.com/paper/2403.11134/) (2024)
- [Motion-Conditioned Diffusion Model for Controllable Video Synthesis](https://mlsanity.com/paper/2304.14404/) (2023)
- [Implicit Identity Representation Conditioned Memory Compensation Network for Talking Head video Generation](https://mlsanity.com/paper/2307.09906/) (2023)
- [Human4DiT: 360-degree Human Video Generation with 4D Diffusion Transformer](https://mlsanity.com/paper/2405.17405/) (2024)
- [ViVid-1-to-3: Novel View Synthesis with Video Diffusion Models](https://mlsanity.com/paper/2312.01305/) (2023)
- [MVHumanNet: A Large-scale Dataset of Multi-view Daily Dressing Human Captures](https://mlsanity.com/paper/2312.02963/) (2023)
- [Structure-Aware Motion Transfer with Deformable Anchor Model](https://mlsanity.com/paper/2204.05018/) (2022)
- [DaGAN++: Depth-Aware Generative Adversarial Network for Talking Head Video Generation](https://mlsanity.com/paper/2305.06225/) (2023)
- [PKU-DyMVHumans: A Multi-View Video Benchmark for High-Fidelity Dynamic Human Modeling](https://mlsanity.com/paper/2403.16080/) (2024)

## Built on by (most cited first, 5 of 5)

- [DreamActor-M1: Holistic, Expressive and Robust Human Image Animation with Hybrid Guidance](https://mlsanity.com/paper/2504.01724/) (2025)
- [Retrieval Augmented Generation and Understanding in Vision: A Survey and New Outlook](https://mlsanity.com/paper/2503.18016/) (2025)
- [UP2You: Fast Reconstruction of Yourself from Unconstrained Photo Collections](https://mlsanity.com/paper/2509.24817/) (2025)
- [MotionWeaver: Holistic 4D-Anchored Framework for Multi-Humanoid Image Animation](https://mlsanity.com/paper/2602.13326/) (2026)
- [Screen, Cache, and Match: A Training-Free Causality-Consistent Reference Frame Framework for Human Animation](https://mlsanity.com/paper/2601.22160/) (2025)

## Abstract (arXiv)

Diffusion-based human animation aims to animate a human character based on a source human image as well as driving signals such as a sequence of poses. Leveraging the generative capacity of diffusion model, existing approaches are able to generate high-fidelity poses, but struggle with significant viewpoint changes, especially in zoom-in/zoom-out scenarios where camera-character distance varies. This limits the applications such as cinematic shot type plan or camera control. We propose a pose-correlated reference selection diffusion network, supporting substantial viewpoint variations in human animation. Our key idea is to enable the network to utilize multiple reference images as input, since significant viewpoint changes often lead to missing appearance details on the human body. To eliminate the computational cost, we first introduce a novel pose correlation module to compute similarities between non-aligned target and source poses, and then propose an adaptive reference selection strategy, utilizing the attention map to identify key regions for animation generation. To train our model, we curated a large dataset from public TED talks featuring varied shots of the same character, helping the model learn synthesis for different perspectives. Our experimental results show that with the same number of reference images, our model performs favorably compared to the current SOTA methods under large viewpoint change. We further show that the adaptive reference selection is able to choose the most relevant reference regions to generate humans under free viewpoints.