# Disentangling Foreground and Background Motion for Enhanced Realism in Human Video Generation

arXiv: https://arxiv.org/abs/2405.16393 · HTML: https://mlsanity.com/paper/2405.16393/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Placed in Video generation, one of 14 directions in Diffusion models.
- Builds on 30 of its 32 references that are in the map.
- First posted on arXiv 26 May 2024.

## Placed in

- Diffusion models / [Video generation](https://mlsanity.com/diffusion/video-generation/)

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

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [DINOv2: Learning Robust Visual Features without Supervision](https://mlsanity.com/paper/2304.07193/) (2023)
- [Neural Discrete Representation Learning](https://mlsanity.com/paper/1711.00937/) (2017)
- [AnimateDiff: Animate Your Personalized Text-to-Image Diffusion Models without Specific Tuning](https://mlsanity.com/paper/2307.04725/) (2023)
- [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)
- [DensePose: Dense Human Pose Estimation In The Wild](https://mlsanity.com/paper/1802.00434/) (2018)
- [CoTracker: It is Better to Track Together](https://mlsanity.com/paper/2307.07635/) (2023)
- [AnyDoor: Zero-shot Object-level Image Customization](https://mlsanity.com/paper/2307.09481/) (2023)
- [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)
- [Champ: Controllable and Consistent Human Image Animation with 3D Parametric Guidance](https://mlsanity.com/paper/2403.14781/) (2024)
- [Motion Representations for Articulated Animation](https://mlsanity.com/paper/2104.11280/) (2021)
- [EMO: Emote Portrait Alive -- Generating Expressive Portrait Videos with Audio2Video Diffusion Model under Weak Conditions](https://mlsanity.com/paper/2402.17485/) (2024)
- [Diffusion Hyperfeatures: Searching Through Time and Space for Semantic Correspondence](https://mlsanity.com/paper/2305.14334/) (2023)
- [Thin-Plate Spline Motion Model for Image Animation](https://mlsanity.com/paper/2203.14367/) (2022)
- [Animating Arbitrary Objects via Deep Motion Transfer](https://mlsanity.com/paper/1812.08861/) (2018)
- [AniPortrait: Audio-Driven Synthesis of Photorealistic Portrait Animation](https://mlsanity.com/paper/2403.17694/) (2024)
- [DreamPose: Fashion Image-to-Video Synthesis via Stable Diffusion](https://mlsanity.com/paper/2304.06025/) (2023)
- [OOTDiffusion: Outfitting Fusion based Latent Diffusion for Controllable Virtual Try-on](https://mlsanity.com/paper/2403.01779/) (2024)
- [DisCo: Disentangled Control for Realistic Human Dance Generation](https://mlsanity.com/paper/2307.00040/) (2023)
- [Unsupervised Semantic Correspondence Using Stable Diffusion](https://mlsanity.com/paper/2305.15581/) (2023)
- [DwNet: Dense warp-based network for pose-guided human video generation](https://mlsanity.com/paper/1910.09139/) (2019)
- [Exploring Dual-task Correlation for Pose Guided Person Image Generation](https://mlsanity.com/paper/2203.02910/) (2022)
- [Boosting Semantic Human Matting with Coarse Annotations](https://mlsanity.com/paper/2004.04955/) (2020)
- [MEVG: Multi-event Video Generation with Text-to-Video Models](https://mlsanity.com/paper/2312.04086/) (2023)
- [Bidirectionally Deformable Motion Modulation For Video-based Human Pose Transfer](https://mlsanity.com/paper/2307.07754/) (2023)
- [Magic Clothing: Controllable Garment-Driven Image Synthesis](https://mlsanity.com/paper/2404.09512/) (2024)

## Built on by (most cited first, 6 of 6)

- [A Comprehensive Survey on Human Video Generation: Challenges, Methods, and Insights](https://mlsanity.com/paper/2407.08428/) (2024)
- [Human Motion Video Generation: A Survey](https://mlsanity.com/paper/2509.03883/) (2025)
- [X-Dyna: Expressive Dynamic Human Image Animation](https://mlsanity.com/paper/2501.10021/) (2025)
- [AnimateAnywhere: Rouse the Background in Human Image Animation](https://mlsanity.com/paper/2504.19834/) (2025)
- [A multidimensional measurement of photorealistic avatar quality of experience](https://mlsanity.com/paper/2411.09066/) (2024)
- [Generating Fit Check Videos with a Handheld Camera](https://mlsanity.com/paper/2505.23886/) (2025)

## Abstract (arXiv)

Recent advancements in human video synthesis have enabled the generation of high-quality videos through the application of stable diffusion models. However, existing methods predominantly concentrate on animating solely the human element (the foreground) guided by pose information, while leaving the background entirely static. Contrary to this, in authentic, high-quality videos, backgrounds often dynamically adjust in harmony with foreground movements, eschewing stagnancy. We introduce a technique that concurrently learns both foreground and background dynamics by segregating their movements using distinct motion representations. Human figures are animated leveraging pose-based motion, capturing intricate actions. Conversely, for backgrounds, we employ sparse tracking points to model motion, thereby reflecting the natural interaction between foreground activity and environmental changes. Training on real-world videos enhanced with this innovative motion depiction approach, our model generates videos exhibiting coherent movement in both foreground subjects and their surrounding contexts. To further extend video generation to longer sequences without accumulating errors, we adopt a clip-by-clip generation strategy, introducing global features at each step. To ensure seamless continuity across these segments, we ingeniously link the final frame of a produced clip with input noise to spawn the succeeding one, maintaining narrative flow. Throughout the sequential generation process, we infuse the feature representation of the initial reference image into the network, effectively curtailing any cumulative color inconsistencies that may otherwise arise. Empirical evaluations attest to the superiority of our method in producing videos that exhibit harmonious interplay between foreground actions and responsive background dynamics, surpassing prior methodologies in this regard.