# Real-Time High-Resolution Background Matting

arXiv: https://arxiv.org/abs/2012.07810 · HTML: https://mlsanity.com/paper/2012.07810/

## Key facts

- Cited by 173 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 14 Dec 2020.

## Built on by (most cited first, 30 of 173)

- [GaussianAvatars: Photorealistic Head Avatars with Rigged 3D Gaussians](https://mlsanity.com/paper/2312.02069/) (2023)
- [Tensor4D : Efficient Neural 4D Decomposition for High-fidelity Dynamic Reconstruction and Rendering](https://mlsanity.com/paper/2211.11610/) (2022)
- [NeRSemble: Multi-view Radiance Field Reconstruction of Human Heads](https://mlsanity.com/paper/2305.03027/) (2023)
- [PAC-NeRF: Physics Augmented Continuum Neural Radiance Fields for Geometry-Agnostic System Identification](https://mlsanity.com/paper/2303.05512/) (2023)
- [Robust High-Resolution Video Matting with Temporal Guidance](https://mlsanity.com/paper/2108.11515/) (2021)
- [Structured Local Radiance Fields for Human Avatar Modeling](https://mlsanity.com/paper/2203.14478/) (2022)
- [DNA-Rendering: A Diverse Neural Actor Repository for High-Fidelity Human-centric Rendering](https://mlsanity.com/paper/2307.10173/) (2023)
- [AvatarReX: Real-time Expressive Full-body Avatars](https://mlsanity.com/paper/2305.04789/) (2023)
- [HiFi4G: High-Fidelity Human Performance Rendering via Compact Gaussian Splatting](https://mlsanity.com/paper/2312.03461/) (2023)
- [SwitchLight: Co-design of Physics-driven Architecture and Pre-training Framework for Human Portrait Relighting](https://mlsanity.com/paper/2402.18848/) (2024)
- [Low-light Image Enhancement via Breaking Down the Darkness](https://mlsanity.com/paper/2111.15557/) (2021)
- [Privacy-Preserving Portrait Matting](https://mlsanity.com/paper/2104.14222/) (2021)
- [FreeTimeGS: Free Gaussian Primitives at Anytime and Anywhere for Dynamic Scene Reconstruction](https://mlsanity.com/paper/2506.05348/) (2025)
- [Avat3r: Large Animatable Gaussian Reconstruction Model for High-fidelity 3D Head Avatars](https://mlsanity.com/paper/2502.20220/) (2025)
- [GIC: Gaussian-Informed Continuum for Physical Property Identification and Simulation](https://mlsanity.com/paper/2406.14927/) (2024)
- [MatteFormer: Transformer-Based Image Matting via Prior-Tokens](https://mlsanity.com/paper/2203.15662/) (2022)
- [NeuralHOFusion: Neural Volumetric Rendering under Human-object Interactions](https://mlsanity.com/paper/2202.12825/) (2022)
- [DiffusionAvatars: Deferred Diffusion for High-fidelity 3D Head Avatars](https://mlsanity.com/paper/2311.18635/) (2023)
- [Generative Omnimatte: Learning to Decompose Video into Layers](https://mlsanity.com/paper/2411.16683/) (2024)
- [HAvatar: High-fidelity Head Avatar via Facial Model Conditioned Neural Radiance Field](https://mlsanity.com/paper/2309.17128/) (2023)
- [GAF: Gaussian Avatar Reconstruction from Monocular Videos via Multi-view Diffusion](https://mlsanity.com/paper/2412.10209/) (2024)
- [Virtual Elastic Objects](https://mlsanity.com/paper/2201.04623/) (2022)
- [Reconstructing Hand-Held Objects from Monocular Video](https://mlsanity.com/paper/2211.16835/) (2022)
- [HHAvatar: Gaussian Head Avatar with Dynamic Hairs](https://mlsanity.com/paper/2312.03029/) (2023)
- [OpenIllumination: A Multi-Illumination Dataset for Inverse Rendering Evaluation on Real Objects](https://mlsanity.com/paper/2309.07921/) (2023)
- [AvatarStudio: Text-driven Editing of 3D Dynamic Human Head Avatars](https://mlsanity.com/paper/2306.00547/) (2023)
- [Multi-view Aggregation Network for Dichotomous Image Segmentation](https://mlsanity.com/paper/2404.07445/) (2024)
- [Attention-guided Temporally Coherent Video Object Matting](https://mlsanity.com/paper/2105.11427/) (2021)
- [Rethinking Portrait Matting with Privacy Preserving](https://mlsanity.com/paper/2203.16828/) (2022)
- [Human Instance Matting via Mutual Guidance and Multi-Instance Refinement](https://mlsanity.com/paper/2205.10767/) (2022)

## Abstract (arXiv)

We introduce a real-time, high-resolution background replacement technique which operates at 30fps in 4K resolution, and 60fps for HD on a modern GPU. Our technique is based on background matting, where an additional frame of the background is captured and used in recovering the alpha matte and the foreground layer. The main challenge is to compute a high-quality alpha matte, preserving strand-level hair details, while processing high-resolution images in real-time. To achieve this goal, we employ two neural networks; a base network computes a low-resolution result which is refined by a second network operating at high-resolution on selective patches. We introduce two largescale video and image matting datasets: VideoMatte240K and PhotoMatte13K/85. Our approach yields higher quality results compared to the previous state-of-the-art in background matting, while simultaneously yielding a dramatic boost in both speed and resolution.