# Generative Video Matting

arXiv: https://arxiv.org/abs/2508.07905 · HTML: https://mlsanity.com/paper/2508.07905/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 23 of its 48 references that are in the map.
- First posted on arXiv 11 Aug 2025.

## Builds on (most cited first, 23 of 23)

- [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)
- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesis](https://mlsanity.com/paper/2307.01952/) (2023)
- [Scaling Rectified Flow Transformers for High-Resolution Image Synthesis](https://mlsanity.com/paper/2403.03206/) (2024)
- [CogVideoX: Text-to-Video Diffusion Models with An Expert Transformer](https://mlsanity.com/paper/2408.06072/) (2024)
- [BEDLAM: A Synthetic Dataset of Bodies Exhibiting Detailed Lifelike Animated Motion](https://mlsanity.com/paper/2306.16940/) (2023)
- [Sapiens: Foundation for Human Vision Models](https://mlsanity.com/paper/2408.12569/) (2024)
- [DynamicStereo: Consistent Dynamic Depth from Stereo Videos](https://mlsanity.com/paper/2305.02296/) (2023)
- [Robust High-Resolution Video Matting with Temporal Guidance](https://mlsanity.com/paper/2108.11515/) (2021)
- [MODNet: Real-Time Trimap-Free Portrait Matting via Objective Decomposition](https://mlsanity.com/paper/2011.11961/) (2020)
- [Transparent Image Layer Diffusion using Latent Transparency](https://mlsanity.com/paper/2402.17113/) (2024)
- [Background Matting: The World is Your Green Screen](https://mlsanity.com/paper/2004.00626/) (2020)
- [Bridging Composite and Real: Towards End-to-end Deep Image Matting](https://mlsanity.com/paper/2010.16188/) (2020)
- [Context-Aware Image Matting for Simultaneous Foreground and Alpha Estimation](https://mlsanity.com/paper/1909.09725/) (2019)
- [CV-VAE: A Compatible Video VAE for Latent Generative Video Models](https://mlsanity.com/paper/2405.20279/) (2024)
- [Privacy-Preserving Portrait Matting](https://mlsanity.com/paper/2104.14222/) (2021)
- [Information-Flow Matting](https://mlsanity.com/paper/1707.05055/) (2017)
- [Rethinking Portrait Matting with Privacy Preserving](https://mlsanity.com/paper/2203.16828/) (2022)
- [Boosting Robustness of Image Matting with Context Assembling and Strong Data Augmentation](https://mlsanity.com/paper/2201.06889/) (2022)
- [MaGGIe: Masked Guided Gradual Human Instance Matting](https://mlsanity.com/paper/2404.16035/) (2024)
- [OmnimatteRF: Robust Omnimatte with 3D Background Modeling](https://mlsanity.com/paper/2309.07749/) (2023)
- [Matting by Generation](https://mlsanity.com/paper/2407.21017/) (2024)

## Built on by (most cited first, 3 of 3)

- [MatAnyone 2: Scaling Video Matting via a Learned Quality Evaluator](https://mlsanity.com/paper/2512.11782/) (2025)
- [VideoMaMa: Mask-Guided Video Matting via Generative Prior](https://mlsanity.com/paper/2601.14255/) (2026)
- [αDepth: Learning Single-Pass Soft Boundary Decomposition for Stereo Conversion](https://mlsanity.com/paper/2606.00386/) (2026)

## Abstract (arXiv)

Video matting has traditionally been limited by the lack of high-quality ground-truth data. Most existing video matting datasets provide only human-annotated imperfect alpha and foreground annotations, which must be composited to background images or videos during the training stage. Thus, the generalization capability of previous methods in real-world scenarios is typically poor. In this work, we propose to solve the problem from two perspectives. First, we emphasize the importance of large-scale pre-training by pursuing diverse synthetic and pseudo-labeled segmentation datasets. We also develop a scalable synthetic data generation pipeline that can render diverse human bodies and fine-grained hairs, yielding around 200 video clips with a 3-second duration for fine-tuning. Second, we introduce a novel video matting approach that can effectively leverage the rich priors from pre-trained video diffusion models. This architecture offers two key advantages. First, strong priors play a critical role in bridging the domain gap between synthetic and real-world scenes. Second, unlike most existing methods that process video matting frame-by-frame and use an independent decoder to aggregate temporal information, our model is inherently designed for video, ensuring strong temporal consistency. We provide a comprehensive quantitative evaluation across three benchmark datasets, demonstrating our approach's superior performance, and present comprehensive qualitative results in diverse real-world scenes, illustrating the strong generalization capability of our method. The code is available at https://github.com/aim-uofa/GVM.