# GaVS: 3D-Grounded Video Stabilization via Temporally-Consistent Local Reconstruction and Rendering

arXiv: https://arxiv.org/abs/2506.23957 · HTML: https://mlsanity.com/paper/2506.23957/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 29 of its 62 references that are in the map.
- First posted on arXiv 30 Jun 2025.

## Builds on (most cited first, 29 of 29)

- [3D Gaussian Splatting for Real-Time Radiance Field Rendering](https://mlsanity.com/paper/2308.04079/) (2023)
- [RAFT: Recurrent All-Pairs Field Transforms for Optical Flow](https://mlsanity.com/paper/2003.12039/) (2020)
- [MVSNeRF: Fast Generalizable Radiance Field Reconstruction from Multi-View Stereo](https://mlsanity.com/paper/2103.15595/) (2021)
- [IBRNet: Learning Multi-View Image-Based Rendering](https://mlsanity.com/paper/2102.13090/) (2021)
- [UniDepth: Universal Monocular Metric Depth Estimation](https://mlsanity.com/paper/2403.18913/) (2024)
- [Single-View View Synthesis with Multiplane Images](https://mlsanity.com/paper/2004.11364/) (2020)
- [Shape of Motion: 4D Reconstruction from a Single Video](https://mlsanity.com/paper/2407.13764/) (2024)
- [Consistent Video Depth Estimation](https://mlsanity.com/paper/2004.15021/) (2020)
- [ProPainter: Improving Propagation and Transformer for Video Inpainting](https://mlsanity.com/paper/2309.03897/) (2023)
- [Stereo Radiance Fields (SRF): Learning View Synthesis for Sparse Views of Novel Scenes](https://mlsanity.com/paper/2104.06935/) (2021)
- [Robust Consistent Video Depth Estimation](https://mlsanity.com/paper/2012.05901/) (2020)
- [MoSca: Dynamic Gaussian Fusion from Casual Videos via 4D Motion Scaffolds](https://mlsanity.com/paper/2405.17421/) (2024)
- [latentSplat: Autoencoding Variational Gaussians for Fast Generalizable 3D Reconstruction](https://mlsanity.com/paper/2403.16292/) (2024)
- [Learning to Render Novel Views from Wide-Baseline Stereo Pairs](https://mlsanity.com/paper/2304.08463/) (2023)
- [Progressively Optimized Local Radiance Fields for Robust View Synthesis](https://mlsanity.com/paper/2303.13791/) (2023)
- [Learning Temporally Consistent Video Depth from Video Diffusion Priors](https://mlsanity.com/paper/2406.01493/) (2024)
- [Dynamic Gaussian Marbles for Novel View Synthesis of Casual Monocular Videos](https://mlsanity.com/paper/2406.18717/) (2024)
- [Layer-structured 3D Scene Inference via View Synthesis](https://mlsanity.com/paper/1807.10264/) (2018)
- [Exploiting temporal consistency for real-time video depth estimation](https://mlsanity.com/paper/1908.03706/) (2019)
- [Depth Any Video with Scalable Synthetic Data](https://mlsanity.com/paper/2410.10815/) (2024)
- [Sora Generates Videos with Stunning Geometrical Consistency](https://mlsanity.com/paper/2402.17403/) (2024)
- [Deep Iterative Frame Interpolation for Full-frame Video Stabilization](https://mlsanity.com/paper/1909.02641/) (2019)
- [Hybrid Neural Fusion for Full-frame Video Stabilization](https://mlsanity.com/paper/2102.06205/) (2021)
- [DUT: Learning Video Stabilization by Simply Watching Unstable Videos](https://mlsanity.com/paper/2011.14574/) (2020)
- [Minimum Latency Deep Online Video Stabilization](https://mlsanity.com/paper/2212.02073/) (2022)
- [Fast Full-frame Video Stabilization with Iterative Optimization](https://mlsanity.com/paper/2307.12774/) (2023)
- [3D Multi-frame Fusion for Video Stabilization](https://mlsanity.com/paper/2404.12887/) (2024)
- [Harnessing Meta-Learning for Improving Full-Frame Video Stabilization](https://mlsanity.com/paper/2403.03662/) (2024)
- [Cinematic-L1 Video Stabilization with a Log-Homography Model](https://mlsanity.com/paper/2011.08144/) (2020)

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

- [Physics-Informed Deformable Gaussian Splatting: Towards Unified Constitutive Laws for Time-Evolving Material Field](https://mlsanity.com/paper/2511.06299/) (2025)
- [OF3GS: On-the-Fly Feed-Forward 3D Gaussian Splatting from Unposed Images](https://mlsanity.com/paper/2606.03254/) (2026)
- [Artificial Microsaccade Compensation: Stable Vision for an Ornithopter](https://mlsanity.com/paper/2512.03995/) (2025)
- [No Labels, No Look-Ahead: Unsupervised Online Video Stabilization with Classical Priors](https://mlsanity.com/paper/2602.23141/) (2026)
- [VS3R: Robust Full-frame Video Stabilization via Deep 3D Reconstruction](https://mlsanity.com/paper/2603.05851/) (2026)

## Abstract (arXiv)

Video stabilization is pivotal for video processing, as it removes unwanted shakiness while preserving the original user motion intent. Existing approaches, depending on the domain they operate, suffer from several issues (e.g. geometric distortions, excessive cropping, poor generalization) that degrade the user experience. To address these issues, we introduce GaVS, a novel 3D-grounded approach that reformulates video stabilization as a temporally-consistent `local reconstruction and rendering' paradigm. Given 3D camera poses, we augment a reconstruction model to predict Gaussian Splatting primitives, and finetune it at test-time, with multi-view dynamics-aware photometric supervision and cross-frame regularization, to produce temporally-consistent local reconstructions. The model are then used to render each stabilized frame. We utilize a scene extrapolation module to avoid frame cropping. Our method is evaluated on a repurposed dataset, instilled with 3D-grounded information, covering samples with diverse camera motions and scene dynamics. Quantitatively, our method is competitive with or superior to state-of-the-art 2D and 2.5D approaches in terms of conventional task metrics and new geometry consistency. Qualitatively, our method produces noticeably better results compared to alternatives, validated by the user study.